On the public citation graph

ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation

https://doi.org/10.1145/3319535.3363216

0 signed · 440 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.

Claim with ORCID

Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.

See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/978-3-030-00470-5_13openalex-snapshot

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks

inferredcites →https://doi.org/10.1007/978-3-030-13453-2_1openalex-snapshot

Label Sanitization Against Label Flipping Poisoning Attacks

inferredcites →https://doi.org/10.1016/j.neunet.2012.02.016openalex-snapshot

Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition

inferredcites →https://doi.org/10.1109/5.726791openalex-snapshot

Gradient-based learning applied to document recognition

inferredcites →https://doi.org/10.1109/9780470544976.ch9openalex-snapshot

GradientBased Learning Applied to Document Recognition

inferredcites →https://doi.org/10.1109/cns.2017.8228656openalex-snapshot

Backdoor attacks against learning systems

inferredcites →https://doi.org/10.1109/cvpr.2009.5206848openalex-snapshot

ImageNet: A large-scale hierarchical image database

inferredcites →https://doi.org/10.1109/cvpr.2016.90openalex-snapshot

Deep Residual Learning for Image Recognition

inferredcites →https://doi.org/10.1109/cvpr.2016.91openalex-snapshot

You Only Look Once: Unified, Real-Time Object Detection

inferredcites →https://doi.org/10.1109/cvpr.2017.17openalex-snapshot

Universal Adversarial Perturbations

inferredcites →https://doi.org/10.1109/cvprw.2015.7301352openalex-snapshot

Age and gender classification using convolutional neural networks

inferredcites →https://doi.org/10.1109/cvprw.2018.00211openalex-snapshot

On the Suitability of Lp-Norms for Creating and Preventing Adversarial Examples

inferredcites →https://doi.org/10.1109/eurosp.2016.36openalex-snapshot

The Limitations of Deep Learning in Adversarial Settings

inferredcites →https://doi.org/10.1109/iccd.2017.16openalex-snapshot

Neural Trojans

inferredcites →https://doi.org/10.1109/iccv.2015.169openalex-snapshot

Fast R-CNN

inferredcites →https://doi.org/10.1109/ijcnn.2011.6033395openalex-snapshot

The German Traffic Sign Recognition Benchmark: A multi-class classification competition

inferredcites →https://doi.org/10.1109/isvlsi.2018.00093openalex-snapshot

Hu-Fu: Hardware and Software Collaborative Attack Framework Against Neural Networks

inferredcites →https://doi.org/10.1109/itsc.2014.6957882openalex-snapshot

Traffic sign detection for U.S. roads: Remaining challenges and a case for tracking

inferredcites →https://doi.org/10.1109/jbhi.2014.2344095openalex-snapshot

Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare

inferredcites →https://doi.org/10.1109/sp.2018.00057openalex-snapshot

Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning

inferredcites →https://doi.org/10.1109/sp.2019.00031openalex-snapshot

Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks

inferredcites →https://doi.org/10.1109/tip.2003.819861openalex-snapshot

Image quality assessment: from error visibility to structural similarity

inferredcites →https://doi.org/10.1145/3052973.3053009openalex-snapshot

Practical Black-Box Attacks against Machine Learning

inferredcites →https://doi.org/10.1145/3134600.3134642openalex-snapshot

Malware Detection in Adversarial Settings

inferredcites →https://doi.org/10.1145/3196494.3196517openalex-snapshot

Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning

inferredcites →https://doi.org/10.1145/3243734.3243757openalex-snapshot

Model-Reuse Attacks on Deep Learning Systems

inferredcites →https://doi.org/10.1145/3274694.3274706openalex-snapshot

Poisoning Attacks to Graph-Based Recommender Systems

inferredcites →https://doi.org/10.14722/ndss.2018.23291openalex-snapshot

Trojaning Attack on Neural Networks

inferredcites →https://doi.org/10.14722/ndss.2019.23415openalex-snapshot

NIC: Detecting Adversarial Samples with Neural Network Invariant Checking

inferredcites →https://doi.org/10.3929/ethz-b-000460348openalex-snapshot

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

inferredcites →https://doi.org/10.48550/arxiv.1312.6199openalex-snapshot

Intriguing properties of neural networks

inferredcites →https://doi.org/10.48550/arxiv.1409.1556openalex-snapshot

Very Deep Convolutional Networks for Large-Scale Image Recognition

inferredcites →https://doi.org/10.48550/arxiv.1711.08001openalex-snapshot

Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training

inferredcites →https://doi.org/10.48550/arxiv.1802.00420openalex-snapshot

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

inferredcites →https://doi.org/10.48550/arxiv.1802.03043openalex-snapshot

PoTrojan: powerful neural-level trojan designs in deep learning models

inferredcites →https://doi.org/10.48550/arxiv.1808.10307openalex-snapshot

Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation

inferredcites →https://doi.org/10.48550/arxiv.1810.11580openalex-snapshot

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

inferredcites →https://doi.org/10.48550/arxiv.1902.06531openalex-snapshot

STRIP: A Defence Against Trojan Attacks on Deep Neural Networks

inferredcites →https://doi.org/10.5244/c.29.41openalex-snapshot

Deep Face Recognition

inferredcites →https://doi.org/10.57702/zp44cu3gopenalex-snapshot

Learning Multiple Layers of Features from Tiny Images

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.2139/ssrn.4578346openalex-extracted

Towards Robustness Evaluation of Backdoor Defense on Quantized Deep Learning Model

inferred← citeshttps://doi.org/10.2139/ssrn.4783051openalex-extracted

inferred← citeshttps://doi.org/10.1002/int.22785openalex-snapshot

A multitarget backdooring attack on deep neural networks with random location trigger

inferred← citeshttps://doi.org/10.1007/978-3-030-58201-2_29openalex-snapshot

Escaping Backdoor Attack Detection of Deep Learning

inferred← citeshttps://doi.org/10.1007/978-3-030-58583-9_20openalex-snapshot

One-Pixel Signature: Characterizing CNN Models for Backdoor Detection

inferred← citeshttps://doi.org/10.1007/978-3-030-58592-1_14openalex-snapshot

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

inferred← citeshttps://doi.org/10.1007/978-3-030-65610-2_4openalex-snapshot

A Defence Against Input-Agnostic Backdoor Attacks on Deep Neural Networks

inferred← citeshttps://doi.org/10.1007/978-3-030-67661-2_18openalex-snapshot

Scalable Backdoor Detection in Neural Networks

inferred← citeshttps://doi.org/10.1007/978-3-030-71522-9_1654openalex-snapshot

Neural Trojans

inferred← citeshttps://doi.org/10.1007/978-3-030-95391-1_47openalex-snapshot

Why is Your Trojan NOT Responding? A Quantitative Analysis of Failures in Backdoor Attacks of Neural Networks

inferred← citeshttps://doi.org/10.1007/978-3-030-98795-4_13openalex-snapshot

Deep Learning Backdoors

inferred← citeshttps://doi.org/10.1007/978-3-031-06365-7_22openalex-snapshot

Understanding the Security of Deepfake Detection

inferred← citeshttps://doi.org/10.1007/978-3-031-13185-1_9openalex-snapshot

Verifying Neural Networks Against Backdoor Attacks

inferred← citeshttps://doi.org/10.1007/978-3-031-17143-7_17openalex-snapshot

Hide and Seek: On the Stealthiness of Attacks Against Deep Learning Systems

inferred← citeshttps://doi.org/10.1007/978-3-031-19778-9_23openalex-snapshot

An Invisible Black-Box Backdoor Attack Through Frequency Domain

inferred← citeshttps://doi.org/10.1007/978-3-031-19839-7_30openalex-snapshot

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

inferred← citeshttps://doi.org/10.1007/978-3-031-20065-6_17openalex-snapshot

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

inferred← citeshttps://doi.org/10.1007/978-3-031-26553-2_22openalex-snapshot

Efficient DNN Backdoor Detection Guided by Static Weight Analysis

inferred← citeshttps://doi.org/10.1007/978-3-031-27481-7_37openalex-snapshot

Backdoor Mitigation in Deep Neural Networks via Strategic Retraining

inferred← citeshttps://doi.org/10.1007/978-3-031-40677-5_13openalex-snapshot

On the Vulnerability of Deep Reinforcement Learning to Backdoor Attacks in Autonomous Vehicles

inferred← citeshttps://doi.org/10.1007/978-3-031-40677-5_16openalex-snapshot

Mitigating Backdoor Attacks on Deep Neural Networks

inferred← citeshttps://doi.org/10.1007/978-3-031-46479-9_9openalex-snapshot

AI Trojan Attacks and Countermeasures

inferred← citeshttps://doi.org/10.1007/978-3-031-50521-8_6openalex-snapshot

AGNES: Abstraction-Guided Framework for Deep Neural Networks Security

inferred← citeshttps://doi.org/10.1007/978-3-031-52265-9_2openalex-snapshot

Can Federated Models Be Rectified Through Learning Negative Gradients?

inferred← citeshttps://doi.org/10.1007/978-3-031-57389-7_3openalex-snapshot

Invisible Backdoor Attacks in Image Classification Based Network Services

inferred← citeshttps://doi.org/10.1007/978-3-031-64954-7_13openalex-snapshot

Do Backdoors Assist Membership Inference Attacks?

inferred← citeshttps://doi.org/10.1007/978-3-031-67826-4_9openalex-snapshot

TrojanInterpret: A Detecting Backdoors Method in DNN Based on Neural Network Interpretation Methods

inferred← citeshttps://doi.org/10.1007/978-3-031-72907-2_3openalex-snapshot

Data Poisoning Quantization Backdoor Attack

inferred← citeshttps://doi.org/10.1007/978-3-031-72970-6_6openalex-snapshot

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing

inferred← citeshttps://doi.org/10.1007/978-3-031-73021-4_24openalex-snapshot

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning

inferred← citeshttps://doi.org/10.1007/978-3-031-73021-4_6openalex-snapshot

Flatness-Aware Sequential Learning Generates Resilient Backdoors

inferred← citeshttps://doi.org/10.1007/978-3-031-73033-7_15openalex-snapshot

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

inferred← citeshttps://doi.org/10.1007/978-3-031-78110-0_18openalex-snapshot

Composite Concept Extraction Through Backdooring

inferred← citeshttps://doi.org/10.1007/978-3-031-78122-3_23openalex-snapshot

TRIGS: Trojan Identification from Gradient-Based Signatures

inferred← citeshttps://doi.org/10.1007/978-3-032-04339-9_9openalex-snapshot

Trojan Vulnerabilities in Host-Based Intrusion Detection Systems

inferred← citeshttps://doi.org/10.1007/978-3-032-07884-1_1openalex-snapshot

Time-Distributed Backdoor Attacks on Federated Spiking Learning

inferred← citeshttps://doi.org/10.1007/978-3-642-27739-9_1654-1openalex-snapshot

Neural Trojans

inferred← citeshttps://doi.org/10.1007/978-981-19-0468-4_1openalex-snapshot

A Backdoor Embedding Method for Backdoor Detection in Deep Neural Networks

inferred← citeshttps://doi.org/10.1007/978-981-19-7554-7_2openalex-snapshot

Ownership Verification Protocols for Deep Neural Network Watermarks

inferred← citeshttps://doi.org/10.1007/978-981-92-2859-1_38openalex-snapshot

Minimal-Overhead Backdoor Detection via Entropy-Guided Activation Substitution

inferred← citeshttps://doi.org/10.1007/978-981-92-3015-0_14openalex-snapshot

CSC: Turning the Adversary’s Poison Against Itself

inferred← citeshttps://doi.org/10.1007/978-981-92-3435-6_40openalex-snapshot

AttnSafe: Detecting Potential Backdoors for LLM via Attention Anomaly Analysis

inferred← citeshttps://doi.org/10.1007/978-981-95-0172-4_17openalex-snapshot

A Color-Based Data Poisoning Backdoor Approach for Misleading Adversarial Privacy Prediction

inferred← citeshttps://doi.org/10.1007/978-981-95-4109-6_33openalex-snapshot

Semantic Consistency Guided Backdoor Trigger Inversion and InitDistillNet for Backdoor Detection

inferred← citeshttps://doi.org/10.1007/978-981-95-5696-0_29openalex-snapshot

Hadamard Transform Based Backdoor Attack

inferred← citeshttps://doi.org/10.1007/978-981-96-0116-5_18openalex-snapshot

BDEL: A Backdoor Attack Defense Method Based on Ensemble Learning

inferred← citeshttps://doi.org/10.1007/978-981-96-8183-9_24openalex-snapshot

Arms Race in Deep Learning: A Survey of Backdoor Defenses and Adaptive Attacks

inferred← citeshttps://doi.org/10.1007/978-981-97-0425-5_11openalex-snapshot

Neuron-Level Inverse Perturbation Against Adversarial Attacks

inferred← citeshttps://doi.org/10.1007/978-981-97-0425-5_16openalex-snapshot

Using Adversarial Examples to against Backdoor Attack in Federated Learning

inferred← citeshttps://doi.org/10.1007/978-981-97-0425-5_19openalex-snapshot

Interpretable White-Box Fairness Testing Through Biased Neuron Identification

inferred← citeshttps://doi.org/10.1007/978-981-97-0425-5_2openalex-snapshot

Feature Transfer-Based Stealthy Poisoning Attack for DNNs

inferred← citeshttps://doi.org/10.1007/978-981-99-1648-1_25openalex-snapshot

A Generic Enhancer for Backdoor Attacks on Deep Neural Networks

inferred← citeshttps://doi.org/10.1007/978-981-99-8148-9_23openalex-snapshot

SDBC: A Novel and Effective Self-Distillation Backdoor Cleansing Approach

inferred← citeshttps://doi.org/10.1007/s00521-024-09506-3openalex-snapshot

Invisible backdoor learning in regional transform domain

inferred← citeshttps://doi.org/10.1007/s00530-022-00965-zopenalex-snapshot

Evil vs evil: using adversarial examples to against backdoor attack in federated learning

inferred← citeshttps://doi.org/10.1007/s10462-024-10797-0openalex-snapshot

Robust and privacy-preserving collaborative training: a comprehensive survey

inferred← citeshttps://doi.org/10.1007/s10489-026-07156-7openalex-snapshot

FBAO: backdoor attack against object detection via frequency noise injection

inferred← citeshttps://doi.org/10.1007/s11432-025-4388-5openalex-snapshot

Artificial intelligence security and privacy: a survey

inferred← citeshttps://doi.org/10.1007/s12083-022-01377-6openalex-snapshot

MP-BADNet$$^+$$: Secure and effective backdoor attack detection and mitigation protocols among multi-participants in private DNNs

inferred← citeshttps://doi.org/10.1016/j.adhoc.2021.102727openalex-snapshot

A collaborative deep learning microservice for backdoor defenses in Industrial IoT networks

inferred← citeshttps://doi.org/10.1016/j.asoc.2024.111907openalex-snapshot

Robust knowledge distillation based on feature variance against backdoored teacher model

inferred← citeshttps://doi.org/10.1016/j.comnet.2026.112656openalex-snapshot

HALO: Revealing the inadequacy of backdoor defenses in encrypted traffic classification

inferred← citeshttps://doi.org/10.1016/j.compag.2024.109557openalex-snapshot

Security threats to agricultural artificial intelligence: Position and perspective

inferred← citeshttps://doi.org/10.1016/j.cviu.2024.104208openalex-snapshot

Invisible backdoor attack with attention and steganography

inferred← citeshttps://doi.org/10.1016/j.eswa.2024.124599openalex-snapshot

Towards robustness evaluation of backdoor defense on quantized deep learning models

inferred← citeshttps://doi.org/10.1016/j.eswa.2024.126355openalex-snapshot

Enhancing robustness of backdoor attacks against backdoor defenses

inferred← citeshttps://doi.org/10.1016/j.eswa.2025.127352openalex-snapshot

FEAT: Frequency Energy Based Backdoor Attack in Deep Neural Networks

inferred← citeshttps://doi.org/10.1016/j.eswa.2025.127830openalex-snapshot

FSBA: Invisible backdoor attacks via frequency domain and singular value decomposition

inferred← citeshttps://doi.org/10.1016/j.inffus.2025.103248openalex-snapshot

Backdoor attacks and defense mechanisms in federated learning: A survey

inferred← citeshttps://doi.org/10.1016/j.ipm.2023.103471openalex-snapshot

Turning backdoors for efficient privacy protection against image retrieval violations

inferred← citeshttps://doi.org/10.1016/j.jnlest.2025.100326openalex-snapshot

A survey of backdoor attacks and defences: From deep neural networks to large language models

inferred← citeshttps://doi.org/10.1016/j.knosys.2024.112565openalex-snapshot

Projan: A probabilistic trojan attack on deep neural networks

inferred← citeshttps://doi.org/10.1016/j.neucom.2020.07.133openalex-snapshot

Defense against neural trojan attacks: A survey

inferred← citeshttps://doi.org/10.1016/j.neucom.2021.04.105openalex-snapshot

Mitigating backdoor attacks in LSTM-based text classification systems by Backdoor Keyword Identification

inferred← citeshttps://doi.org/10.1016/j.neucom.2024.128752openalex-snapshot

Correcting the distribution of batch normalization signals for Trojan mitigation

inferred← citeshttps://doi.org/10.1016/j.neucom.2025.130296openalex-snapshot

Invisible trigger image: A dynamic neural backdoor attack based on hidden feature

inferred← citeshttps://doi.org/10.1016/j.patcog.2024.111262openalex-snapshot

A trigger-perceivable backdoor attack framework driven by image steganography

inferred← citeshttps://doi.org/10.1016/j.patcog.2026.114565openalex-snapshot

BadDenoise: Backdoor attacks on self-supervised image denoising

inferred← citeshttps://doi.org/10.1088/1674-1056/acd8abopenalex-snapshot

A backdoor attack against quantum neural networks with limited information

inferred← citeshttps://doi.org/10.1109/access.2022.3141077openalex-snapshot

A Feature-Based On-Line Detector to Remove Adversarial-Backdoors by Iterative Demarcation

inferred← citeshttps://doi.org/10.1109/access.2023.3306333openalex-snapshot

A Novel Framework for Smart Cyber Defence: A Deep-Dive Into Deep Learning Attacks and Defences

inferred← citeshttps://doi.org/10.1109/access.2023.3326410openalex-snapshot

A Survey on Attacks and Their Countermeasures in Deep Learning: Applications in Deep Neural Networks, Federated, Transfer, and Deep Reinforcement Learning

inferred← citeshttps://doi.org/10.1109/access.2023.3339542openalex-snapshot

A Novel Semi-Supervised Adversarially Learned Meta-Classifier for Detecting Neural Trojan Attacks

inferred← citeshttps://doi.org/10.1109/access.2024.3355816openalex-snapshot

Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research Directions

inferred← citeshttps://doi.org/10.1109/access.2024.3382584openalex-snapshot

A Comprehensive Survey on Backdoor Attacks and Their Defenses in Face Recognition Systems

inferred← citeshttps://doi.org/10.1109/access.2024.3423323openalex-snapshot

A Systematic Review of Adversarial Machine Learning Attacks, Defensive Controls, and Technologies

inferred← citeshttps://doi.org/10.1109/access.2024.3455090openalex-snapshot

Adversary Aware Continual Learning

inferred← citeshttps://doi.org/10.1109/access.2025.3543333openalex-snapshot

Detecting All-to-One Backdoor Attacks in Black-Box DNNs via Differential Robustness to Noise

inferred← citeshttps://doi.org/10.1109/access.2025.3571995openalex-snapshot

Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future Prospects

inferred← citeshttps://doi.org/10.1109/access.2026.3659007openalex-snapshot

A Multi-Stage Backdoor Detection (MSBD) Framework

inferred← citeshttps://doi.org/10.1109/access.2026.3709411openalex-snapshot

A4O-Attack: All Triggers for One Sample Backdoor Attacks

inferred← citeshttps://doi.org/10.1109/acomp50827.2020.00010openalex-snapshot

Data Poisoning Attack on Deep Neural Network and Some Defense Methods

inferred← citeshttps://doi.org/10.1109/acsac63791.2024.00078openalex-snapshot

Exploring Inherent Backdoors in Deep Learning Models

inferred← citeshttps://doi.org/10.1109/allerton63246.2024.10735305openalex-snapshot

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges

inferred← citeshttps://doi.org/10.1109/anzcc59813.2024.10432866openalex-snapshot

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

inferred← citeshttps://doi.org/10.1109/bigdata52589.2021.9671910openalex-snapshot

Resisting Distributed Backdoor Attacks in Federated Learning: A Dynamic Norm Clipping Approach

inferred← citeshttps://doi.org/10.1109/bigdata52589.2021.9671964openalex-snapshot

A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples

inferred← citeshttps://doi.org/10.1109/comsnets59351.2024.10427172openalex-snapshot

Backdoor Attacks and Generative Model Fairness: Current Trends and Future Research Directions

inferred← citeshttps://doi.org/10.1109/crsit66101.2025.11141641openalex-snapshot

A Multi-Layer Aggregation Backdoor Defense Framework for Federated Learning

inferred← citeshttps://doi.org/10.1109/cvpr46437.2021.00614openalex-snapshot

Backdoor Attacks Against Deep Learning Systems in the Physical World

inferred← citeshttps://doi.org/10.1109/cvpr52688.2022.01299openalex-snapshot

Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/cvpr52688.2022.01301openalex-snapshot

Better Trigger Inversion Optimization in Backdoor Scanning

inferred← citeshttps://doi.org/10.1109/cvpr52688.2022.01458openalex-snapshot

Complex Backdoor Detection by Symmetric Feature Differencing

inferred← citeshttps://doi.org/10.1109/cvpr52688.2022.01465openalex-snapshot

BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning

inferred← citeshttps://doi.org/10.1109/cvpr52729.2023.00784openalex-snapshot

Single Image Backdoor Inversion via Robust Smoothed Classifiers

inferred← citeshttps://doi.org/10.1109/cvpr52729.2023.00786openalex-snapshot

Color Backdoor: A Robust Poisoning Attack in Color Space

inferred← citeshttps://doi.org/10.1109/cvpr52729.2023.01569openalex-snapshot

Detecting Backdoors in Pre-trained Encoders

inferred← citeshttps://doi.org/10.1109/cvpr52729.2023.01962openalex-snapshot

MEDIC: Remove Model Backdoors via Importance Driven Cloning

inferred← citeshttps://doi.org/10.1109/cvpr52729.2023.01963openalex-snapshot

Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks

inferred← citeshttps://doi.org/10.1109/cvpr52733.2024.02335openalex-snapshot

Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models

inferred← citeshttps://doi.org/10.1109/cvpr52733.2024.02342openalex-snapshot

Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

inferred← citeshttps://doi.org/10.1109/cvpr52734.2025.02402openalex-snapshot

Invisible Backdoor Attack against Self-supervised Learning

inferred← citeshttps://doi.org/10.1109/cvpr52734.2025.02785openalex-snapshot

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models

inferred← citeshttps://doi.org/10.1109/cvprw59228.2023.00230openalex-snapshot

Don’t FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs

inferred← citeshttps://doi.org/10.1109/cvprw63382.2024.00348openalex-snapshot

Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition

inferred← citeshttps://doi.org/10.1109/dsn-w60302.2024.00021openalex-snapshot

Unlearning Backdoor Attacks Through Gradient-Based Model Pruning

inferred← citeshttps://doi.org/10.1109/dsn-w60302.2024.00024openalex-snapshot

Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks

inferred← citeshttps://doi.org/10.1109/eurosp51992.2021.00022openalex-snapshot

Trojaning Language Models for Fun and Profit

inferred← citeshttps://doi.org/10.1109/eurosp53844.2022.00048openalex-snapshot

TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors

inferred← citeshttps://doi.org/10.1109/eurosp53844.2022.00049openalex-snapshot

Dynamic Backdoor Attacks Against Machine Learning Models

inferred← citeshttps://doi.org/10.1109/eurosp57164.2023.00072openalex-snapshot

Watermarking Graph Neural Networks based on Backdoor Attacks

inferred← citeshttps://doi.org/10.1109/fmec59375.2023.10306137openalex-snapshot

Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification

inferred← citeshttps://doi.org/10.1109/icaa58325.2023.00019openalex-snapshot

Detecting Trojaned DNNs Using Counterfactual Attributions

inferred← citeshttps://doi.org/10.1109/icaiic60209.2024.10463411openalex-snapshot

Defense Method Challenges Against Backdoor Attacks in Neural Networks

inferred← citeshttps://doi.org/10.1109/icassp48485.2024.10448222openalex-snapshot

Ten-Guard: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/icassp49357.2023.10097244openalex-snapshot

Training Set Cleansing of Backdoor Poisoning by Self-Supervised Representation Learning

inferred← citeshttps://doi.org/10.1109/icassp49660.2025.10888729openalex-snapshot

Distill To Detect: Amplifying Anomalies in Backdoor Models through Knowledge Distillation

inferred← citeshttps://doi.org/10.1109/icassp49660.2025.10889523openalex-snapshot

BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution

inferred← citeshttps://doi.org/10.1109/icassp55912.2026.11461613openalex-snapshot

Exploiting Backdoor Trigger Towards Unlearnable Examples

inferred← citeshttps://doi.org/10.1109/icbdml68582.2026.11544990openalex-snapshot

Adversarial Machine Learning Attacks and Defenses in Next-Generation Cybersecurity Applications

inferred← citeshttps://doi.org/10.1109/icc51166.2024.10622312openalex-snapshot

Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/icc59461.2026.11588139openalex-snapshot

When Guidance Turns Poisonous: Backdooring the SAR-guided Cloud Removal Model

inferred← citeshttps://doi.org/10.1109/iccbdai66607.2025.11388596openalex-snapshot

Reinforcement Learning-Based Defense Framework Against Backdoor Attacks in Deep Learning Models

inferred← citeshttps://doi.org/10.1109/iccc59590.2023.10507399openalex-snapshot

Backdoor Attack Detecting and Removing Based on Knowledge Distillation for Natural Language Translation Model

inferred← citeshttps://doi.org/10.1109/iccv48922.2021.01614openalex-snapshot

CLEAR: Clean-up Sample-Targeted Backdoor in Neural Networks

inferred← citeshttps://doi.org/10.1109/iccv51070.2023.00403openalex-snapshot

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning

inferred← citeshttps://doi.org/10.1109/iccv51070.2023.00433openalex-snapshot

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

inferred← citeshttps://doi.org/10.1109/iccv51701.2025.00167openalex-snapshot

Backdoor Defense via Enhanced Splitting and Trap Isolation

inferred← citeshttps://doi.org/10.1109/iccv51701.2025.00212openalex-snapshot

Prototype Guided Backdoor Defense via Activation Space Manipulation

inferred← citeshttps://doi.org/10.1109/iccv51701.2025.00306openalex-snapshot

DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion

inferred← citeshttps://doi.org/10.1109/iccv51701.2025.00412openalex-snapshot

Backdoor Attacks on Neural Networks Via One-Bit Flip

inferred← citeshttps://doi.org/10.1109/iccvw54120.2021.00008openalex-snapshot

Trojan Signatures in DNN Weights

inferred← citeshttps://doi.org/10.1109/icdcs57875.2023.00011openalex-snapshot

ScanFed: Scalable Behavior-Based Backdoor Detection in Federated Learning

inferred← citeshttps://doi.org/10.1109/icde53745.2022.00100openalex-snapshot

Towards Backdoor Attack on Deep Learning based Time Series Classification

inferred← citeshttps://doi.org/10.1109/icdm50108.2020.00025openalex-snapshot

Towards Inspecting and Eliminating Trojan Backdoors in Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/icicml60161.2023.10424802openalex-snapshot

DaBA: Data-free Backdoor Attack against Federated Learning via Malicious Server

inferred← citeshttps://doi.org/10.1109/icmla58977.2023.00271openalex-snapshot

Dormant Neural Trojans

inferred← citeshttps://doi.org/10.1109/icmlc51923.2020.9469037openalex-snapshot

Segmentation Based Backdoor Attack Detection

inferred← citeshttps://doi.org/10.1109/icmlc66258.2025.11280213openalex-snapshot

Band-Aid Backdoor: A Dual-Branch Framework for Physical Backdoor Attacks on Face Recognition Systems

inferred← citeshttps://doi.org/10.1109/icscai61790.2024.10867068openalex-snapshot

Protecting Deep Neural Networks in Cloud-Based Environments Towards Backdoor Assaults

inferred← citeshttps://doi.org/10.1109/icsccc69031.2026.11600379openalex-snapshot

Detecting Backdoored Models using Gradient Entropy Analysis of Adversarial Inputs

inferred← citeshttps://doi.org/10.1109/ictc58733.2023.10393379openalex-snapshot

X-HDNN: Explainable Hybrid DNN for Industrial Internet of Things Backdoor Attack Detection

inferred← citeshttps://doi.org/10.1109/ijcnn54540.2023.10191661openalex-snapshot

Backdoor Attack on Deep Neural Networks in Perception Domain

inferred← citeshttps://doi.org/10.1109/ijcnn60899.2024.10650468openalex-snapshot

OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection

inferred← citeshttps://doi.org/10.1109/ijcnn60899.2024.10651046openalex-snapshot

Data-Free Backdoor Model Inspection: Masking and Reverse Engineering Loops for Feature Counting

inferred← citeshttps://doi.org/10.1109/ijcnn64981.2025.11227981openalex-snapshot

DeBUGCN - Detecting Backdoors in CNNs Using Graph Convolutional Networks

inferred← citeshttps://doi.org/10.1109/ijcnn64981.2025.11228380openalex-snapshot

Backdoor Defense via Malicious Knowledge Capturing and Machine Unlearning with Out-of-Distribution Data

inferred← citeshttps://doi.org/10.1109/ikt69652.2025.11626733openalex-snapshot

Detection of Backdoor Attacks in Neural Networks Using Input Optimization

inferred← citeshttps://doi.org/10.1109/infocom48880.2022.9796878openalex-snapshot

TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers

inferred← citeshttps://doi.org/10.1109/infocom59046.2026.11571574openalex-snapshot

TrojanEdge: Mutual Information-Enhanced Robust and Persistent Backdoor Attacks for Edge and On-Device Deployments

inferred← citeshttps://doi.org/10.1109/ipccc59868.2024.10850041openalex-snapshot

Curse to Blessing: Leveraging Model Inversion Attacks to Detect Backdoor Attacks in Federated Learning

inferred← citeshttps://doi.org/10.1109/isqed48828.2020.9137011openalex-snapshot

A Survey on Neural Trojans

inferred← citeshttps://doi.org/10.1109/iwqos61813.2024.10682906openalex-snapshot

FedTrojan: Corrupting Federated Learning via Zero-Knowledge Federated Trojan Attacks

inferred← citeshttps://doi.org/10.1109/jetcas.2024.3476386openalex-snapshot

On Function-Coupled Watermarks for Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/jiot.2026.3680800openalex-snapshot

GhostBackdoor: A Resistant Backdoor Attack

inferred← citeshttps://doi.org/10.1109/jsac.2021.3087237openalex-snapshot

Defense-Resistant Backdoor Attacks Against Deep Neural Networks in Outsourced Cloud Environment

inferred← citeshttps://doi.org/10.1109/milcom64451.2025.11310745openalex-snapshot

Model-agnostic clean-label backdoor mitigation in cybersecurity environments

inferred← citeshttps://doi.org/10.1109/mlsp58920.2024.10734765openalex-snapshot

Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection

inferred← citeshttps://doi.org/10.1109/mlsp62443.2025.11204213openalex-snapshot

Backdoor Inversion in Neural-Activation Space

inferred← citeshttps://doi.org/10.1109/mwscas67364.2026.11680668openalex-snapshot

TrustNoC: Trustworthy On-Interposer NoC for AI Backdoor Mitigation in Chiplet Systems

inferred← citeshttps://doi.org/10.1109/ojcoms.2024.3518503openalex-snapshot

Private Data Protection With Machine Unlearning for Next-Generation Networks

inferred← citeshttps://doi.org/10.1109/ojsp.2022.3190213openalex-snapshot

An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences

inferred← citeshttps://doi.org/10.1109/raid67961.2025.00025openalex-snapshot

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks

inferred← citeshttps://doi.org/10.1109/satml54575.2023.00031openalex-snapshot

“Real Attackers Don't Compute Gradients”: Bridging the Gap Between Adversarial ML Research and Practice

inferred← citeshttps://doi.org/10.1109/satml54575.2023.00033openalex-snapshot

Sniper Backdoor: Single Client Targeted Backdoor Attack in Federated Learning

inferred← citeshttps://doi.org/10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00246openalex-snapshot

A Novel Backdoor Attack Adapted to Transfer Learning

inferred← citeshttps://doi.org/10.1109/socc56010.2022.9908113openalex-snapshot

Inconspicuous Data Augmentation Based Backdoor Attack on Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/sp46214.2022.9833579openalex-snapshot

Piccolo: Exposing Complex Backdoors in NLP Transformer Models

inferred← citeshttps://doi.org/10.1109/sp46214.2022.9833644openalex-snapshot

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

inferred← citeshttps://doi.org/10.1109/sp46214.2022.9833688openalex-snapshot

Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security

inferred← citeshttps://doi.org/10.1109/sp46215.2023.10179375openalex-snapshot

Redeem Myself: Purifying Backdoors in Deep Learning Models using Self Attention Distillation

inferred← citeshttps://doi.org/10.1109/sp46215.2023.10179473openalex-snapshot

AI-Guardian: Defeating Adversarial Attacks using Backdoors

inferred← citeshttps://doi.org/10.1109/sp46215.2023.10351028openalex-snapshot

Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00015openalex-snapshot

MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00021openalex-snapshot

SoK: Explainable Machine Learning in Adversarial Environments

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00029openalex-snapshot

Distribution Preserving Backdoor Attack in Self-supervised Learning

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00099openalex-snapshot

MEA-Defender: A Robust Watermark against Model Extraction Attack

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00119openalex-snapshot

OdScan: Backdoor Scanning for Object Detection Models

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00174openalex-snapshot

Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00179openalex-snapshot

Poisoning Web-Scale Training Datasets is Practical

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00216openalex-snapshot

Need for Speed: Taming Backdoor Attacks with Speed and Precision

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00225openalex-snapshot

Exploring the Orthogonality and Linearity of Backdoor Attacks

inferred← citeshttps://doi.org/10.1109/sp54263.2024.00226openalex-snapshot

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting

inferred← citeshttps://doi.org/10.1109/sp61157.2025.00094openalex-snapshot

Preference Poisoning Attacks on Reward Model Learning

inferred← citeshttps://doi.org/10.1109/sp61157.2025.00103openalex-snapshot

BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target

inferred← citeshttps://doi.org/10.1109/spcnc68200.2025.11406437openalex-snapshot

Adaptive Fine-Tuning Attacks for Watermark Removal in Deep Models

inferred← citeshttps://doi.org/10.1109/tai.2024.3373720openalex-snapshot

A Subspace Projective Clustering Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/tai.2024.3384938openalex-snapshot

IOTM: Iterative Optimization Trigger Method—A Runtime Data-Free Backdoor Attacks on Deep Neural Networks

inferred← citeshttps://doi.org/10.1109/tase.2025.3589764openalex-snapshot

Shortcut-Enhanced Multimodal Backdoor Attack in Vision-Guided Robot Grasping

inferred← citeshttps://doi.org/10.1109/tbiom.2021.3132132openalex-snapshot

FaceHack: Attacking Facial Recognition Systems Using Malicious Facial Characteristics

showing the first 200 of 400

Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.