On the public citation graph

Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey

0 signed · 118 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 See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.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/10.1016/j.aiopen.2023.08.012openalex-snapshot
GPT understands, too
inferredcites →https://doi.org/10.1016/j.cose.2021.102433openalex-snapshot
BDDR: An Effective Defense Against Textual Backdoor Attacks
inferredcites →https://doi.org/10.1016/j.csi.2023.103827openalex-snapshot
Local differential privacy and its applications: A comprehensive survey
inferredcites →https://doi.org/10.1016/j.hcc.2024.100211openalex-snapshot
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
inferredcites →https://doi.org/10.1016/j.jiixd.2023.10.007openalex-snapshot
Unveiling security, privacy, and ethical concerns of ChatGPT
inferredcites →https://doi.org/10.1038/s41586-023-06647-8openalex-snapshot
Role play with large language models
inferredcites →https://doi.org/10.1109/access.2023.3300381openalex-snapshot
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy
inferredcites →https://doi.org/10.1109/icassp48485.2024.10446267openalex-snapshot
PoisonPrompt: Backdoor Attack on Prompt-Based Large Language Models
inferredcites →https://doi.org/10.1109/iccv.2015.11openalex-snapshot
Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books
inferredcites →https://doi.org/10.1109/icmc60390.2024.00008openalex-snapshot
On Protecting the Data Privacy of Large Language Models (LLMs): A Survey
inferredcites →https://doi.org/10.1109/mnet.2024.3367788openalex-snapshot
A Comprehensive Overview of Backdoor Attacks in Large Language Models Within Communication Networks
inferredcites →https://doi.org/10.1109/sp54263.2024.00123openalex-snapshot
SneakyPrompt: Jailbreaking Text-to-image Generative Models
inferredcites →https://doi.org/10.1109/sp54263.2024.00207openalex-snapshot
Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
inferredcites →https://doi.org/10.1109/tdsc.2021.3055844openalex-snapshot
Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks
inferredcites →https://doi.org/10.1109/tdsc.2024.3372777openalex-snapshot
PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents
inferredcites →https://doi.org/10.1109/tifs.2022.3233190openalex-snapshot
Label-Only Model Inversion Attacks: Attack With the Least Information
inferredcites →https://doi.org/10.1109/tifs.2024.3376968openalex-snapshot
BDMMT: Backdoor Sample Detection for Language Models Through Model Mutation Testing
inferredcites →https://doi.org/10.1145/2976749.2978318openalex-snapshot
Deep Learning with Differential Privacy
inferredcites →https://doi.org/10.1145/3543507.3583348openalex-snapshot
Training-free Lexical Backdoor Attacks on Language Models
inferredcites →https://doi.org/10.1145/3547330openalex-snapshot
Adversarial Attacks and Defenses in Deep Learning: From a Perspective of Cybersecurity
inferredcites →https://doi.org/10.1145/3548606.3560675openalex-snapshot
Enhanced Membership Inference Attacks against Machine Learning Models
inferredcites →https://doi.org/10.1145/3576915openalex-snapshot
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security
inferredcites →https://doi.org/10.1145/3576915.3616652openalex-snapshot
Stealing the Decoding Algorithms of Language Models
inferredcites →https://doi.org/10.1145/3579856.3582829openalex-snapshot
CASSOCK: Viable Backdoor Attacks against DNN in the Wall of Source-Specific Backdoor Defenses
inferredcites →https://doi.org/10.1145/3597503.3623326openalex-snapshot
UniLog: Automatic Logging via LLM and In-Context Learning
inferredcites →https://doi.org/10.1145/3597503.3639091openalex-snapshot
On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study
inferredcites →https://doi.org/10.1145/3605764.3623985openalex-snapshot
Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
inferredcites →https://doi.org/10.1145/3658644.3670361openalex-snapshot
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
inferredcites →https://doi.org/10.1145/3658644.3670370openalex-snapshot
PLeak: Prompt Leaking Attacks against Large Language Model Applications
inferredcites →https://doi.org/10.1145/3658644.3670388openalex-snapshot
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
inferredcites →https://doi.org/10.1145/3658644.3690291openalex-snapshot
Optimization-based Prompt Injection Attack to LLM-as-a-Judge
inferredcites →https://doi.org/10.1145/3658644.3690306openalex-snapshot
Membership Inference Attacks Against In-Context Learning
inferredcites →https://doi.org/10.1145/3658644.3690322openalex-snapshot
Legilimens: Practical and Unified Content Moderation for Large Language Model Services
inferredcites →https://doi.org/10.1145/3663530.3665021openalex-snapshot
A Hitchhiker’s Guide to Jailbreaking ChatGPT via Prompt Engineering
inferredcites →https://doi.org/10.1145/3712001openalex-snapshot
Security and Privacy Challenges of Large Language Models: A Survey
inferredcites →https://doi.org/10.14722/ndss.2024.24090openalex-snapshot
TextGuard: Provable Defense against Backdoor Attacks on Text Classification
inferredcites →https://doi.org/10.14722/ndss.2025.230478openalex-snapshot
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
inferredcites →https://doi.org/10.18653/v1/2020.emnlp-main.346openalex-snapshot
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
inferredcites →https://doi.org/10.18653/v1/2021.emnlp-main.243openalex-snapshot
The Power of Scale for Parameter-Efficient Prompt Tuning
inferredcites →https://doi.org/10.18653/v1/2021.emnlp-main.464openalex-snapshot
Gradient-based Adversarial Attacks against Text Transformers
inferredcites →https://doi.org/10.18653/v1/2021.emnlp-main.752openalex-snapshot
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
inferredcites →https://doi.org/10.18653/v1/2021.naacl-mainopenalex-snapshot
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
inferredcites →https://doi.org/10.18653/v1/2022.acl-long.469openalex-snapshot
ParaDetox: Detoxification with Parallel Data
inferredcites →https://doi.org/10.18653/v1/2022.acl-short.8openalex-snapshot
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks
inferredcites →https://doi.org/10.18653/v1/2022.emnlp-main.323openalex-snapshot
Differentially Private Language Models for Secure Data Sharing
inferredcites →https://doi.org/10.18653/v1/2022.findings-acl.277openalex-snapshot
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption
inferredcites →https://doi.org/10.18653/v1/2022.naacl-main.205openalex-snapshot
Selective Differential Privacy for Language Modeling
inferredcites →https://doi.org/10.18653/v1/2023.acl-long.20openalex-snapshot
Text Adversarial Purification as Defense against Adversarial Attacks
inferredcites →https://doi.org/10.18653/v1/2023.acl-long.244openalex-snapshot
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
inferredcites →https://doi.org/10.18653/v1/2023.acl-long.423openalex-snapshot
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
inferredcites →https://doi.org/10.18653/v1/2023.acl-long.709openalex-snapshot
ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
inferredcites →https://doi.org/10.18653/v1/2023.acl-long.725openalex-snapshot
BITE: Textual Backdoor Attacks with Iterative Trigger Injection
inferredcites →https://doi.org/10.18653/v1/2023.emnlp-main.757openalex-snapshot
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
inferredcites →https://doi.org/10.18653/v1/2023.emnlp-main.765openalex-snapshot
Text Embeddings Reveal (Almost) As Much As Text
inferredcites →https://doi.org/10.18653/v1/2023.findings-acl.719openalex-snapshot
Membership Inference Attacks against Language Models via Neighbourhood Comparison
inferredcites →https://doi.org/10.18653/v1/2023.findings-emnlp.88openalex-snapshot
Toxicity in chatgpt: Analyzing persona-assigned language models
inferredcites →https://doi.org/10.18653/v1/2023.inlg-main.28openalex-snapshot
Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
inferredcites →https://doi.org/10.18653/v1/2023.trustnlp-1.18openalex-snapshot
Detecting Personal Information in Training Corpora: an Analysis
inferredcites →https://doi.org/10.18653/v1/2024.acl-long.140openalex-snapshot
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
inferredcites →https://doi.org/10.18653/v1/2024.emnlp-main.785openalex-snapshot
Large Language Models Can Be Contextual Privacy Protection Learners
inferredcites →https://doi.org/10.18653/v1/2024.naacl-long.337openalex-snapshot
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
inferredcites →https://doi.org/10.18653/v1/2024.naacl-long.375openalex-snapshot
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
inferredcites →https://doi.org/10.18653/v1/2025.acl-long.1227openalex-snapshot
Unveiling Privacy Risks in LLM Agent Memory
inferredcites →https://doi.org/10.18653/v1/2025.acl-long.359openalex-snapshot
G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems
inferredcites →https://doi.org/10.18653/v1/2025.naacl-long.101openalex-snapshot
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
inferredcites →https://doi.org/10.23919/eusipco58844.2023.10289979openalex-snapshot
A Relaxed Optimization Approach for Adversarial Attacks Against Neural Machine Translation Models
inferredcites →https://doi.org/10.4135/9781452276250.n118openalex-snapshot
Health Insurance Portability and Accountability Act
inferredcites →https://doi.org/10.52202/068431-0362openalex-snapshot
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
inferredcites →https://doi.org/10.52202/068431-2686openalex-snapshot
BadPrompt: Backdoor Attacks on Continuous Prompts
inferredcites →https://doi.org/10.52202/075280-2703openalex-snapshot
On the Exploitability of Instruction Tuning
inferredcites →https://doi.org/10.52202/079017-3201openalex-snapshot
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
inferredcites →https://doi.org/10.56553/popets-2024-0075openalex-snapshot
TMI! Finetuned Models Leak Private Information from their Pretraining Data
inferredcites →https://doi.org/10.69554/kzrs2422openalex-snapshot
Machine unlearning for generative AI

What points at this work

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

inferred← citeshttps://doi.org/10.1007/978-3-032-23607-4_19openalex-snapshot
The Next Stage of Evolutionary Computation in the Era of Agentic Generative AI
inferred← citeshttps://doi.org/10.1007/978-3-032-32578-5_5openalex-snapshot
A Theoretical Framework for the Security of Multi-stage LLM Output Filtering Pipelines
inferred← citeshttps://doi.org/10.1007/s11119-026-10349-2openalex-snapshot
Emerging roles of large language models (LLMs) in smart farming and precision agriculture: security challenges, threat taxonomy, and mitigation strategies
inferred← citeshttps://doi.org/10.1007/s11831-026-10680-xopenalex-snapshot
Security, Privacy, and Ethical Challenges in Large Language Models: A Review
inferred← citeshttps://doi.org/10.1016/j.asoc.2024.112663openalex-snapshot
Large language models for cyber resilience: A comprehensive review, challenges, and future perspectives
inferred← citeshttps://doi.org/10.1016/j.comnet.2025.111379openalex-snapshot
A comprehensive survey on large language models for multimedia data security: challenges and solutions
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.cosrev.2026.100916openalex-snapshot
LLM in the middle: A systematic review of threats and mitigations to real-world LLM-based systems
inferred← citeshttps://doi.org/10.1016/j.hcc.2025.100300openalex-snapshot
On protecting the data privacy of Large Language Models (LLMs) and LLM agents: A literature review
inferred← citeshttps://doi.org/10.1016/j.ijpe.2026.110247openalex-snapshot
A patent-driven SCOR-IFCM framework to prioritize generative AI adoption for supply chain resilience
inferred← citeshttps://doi.org/10.1016/j.knosys.2026.115848openalex-snapshot
Selective layer-wise cleansing: A knowledge-preserving defense against backdoor attacks in LoRA-tuned models for natural language understanding
inferred← citeshttps://doi.org/10.1016/j.knosys.2026.116100openalex-snapshot
Shortening the prefix! Members and non-members exhibit divergent behavior
inferred← citeshttps://doi.org/10.1016/j.neucom.2026.134939openalex-snapshot
Prompt-based attacks and defenses in large language models: A systematic review of threat models, taxonomies, and evaluation practices
inferred← citeshttps://doi.org/10.1016/j.neunet.2026.109280openalex-snapshot
Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems
inferred← citeshttps://doi.org/10.1080/23742917.2026.2742248openalex-snapshot
Explainable multi-modal Vision Transformer fusion for malware classification
inferred← citeshttps://doi.org/10.1080/27525783.2026.2645373openalex-snapshot
D2M (design-to-manufacturing) by integrating digital twins and large language models: conceptual framework
inferred← citeshttps://doi.org/10.1109/3scea68071.2026.11603054openalex-snapshot
Encoding Book Evasion Technique to Bypass LLMs Defenses
inferred← citeshttps://doi.org/10.1109/access.2026.3658308openalex-snapshot
The AI-Cybersecurity Nexus: How Large Language Models are Reshaping Threat Intelligence and Digital Defense
inferred← citeshttps://doi.org/10.1109/access.2026.3665980openalex-snapshot
A Secure and Efficient LLM-Based System for Natural Language Query-to-SQL Translation in IoT Data Management
inferred← citeshttps://doi.org/10.1109/aiware69974.2025.00027openalex-snapshot
Promptexp: Multi-Granularity Prompt Explanation of Large Language Models
inferred← citeshttps://doi.org/10.1109/cai68641.2026.11536475openalex-snapshot
A Privacy-Preserving Framework for Cyber Incident Analysis from Network Packets Using +Large Language Models
inferred← citeshttps://doi.org/10.1109/ccwc62904.2025.10903912openalex-snapshot
Privacy and Security Challenges in Large Language Models
inferred← citeshttps://doi.org/10.1109/icde65706.2026.00291openalex-snapshot
Building and Benchmarking Large Language Models for Machine Translation in Social Network Services
inferred← citeshttps://doi.org/10.1109/icicgr68236.2026.11600123openalex-snapshot
Ethical Prompt Optimization for Mental Health Chatbots Using Mixture-of-Experts (MoE) and Guardrail LLMs
inferred← citeshttps://doi.org/10.1109/icicip67436.2026.11417533openalex-snapshot
Automatic Department Performance Assessment via Strategic Prompt Engineering
inferred← citeshttps://doi.org/10.1109/iciice69672.2026.11565266openalex-snapshot
Toward Trustworthy Privacy-Preserving AI: Security, Ethics, and Governance Perspectives
inferred← citeshttps://doi.org/10.1109/ojcoms.2026.3680064openalex-snapshot
LLMs and IoT: A Comprehensive Survey on Large Language Models and the Internet of Things
inferred← citeshttps://doi.org/10.1109/satml68715.2026.00039openalex-snapshot
SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
inferred← citeshttps://doi.org/10.1109/southeastcon63549.2026.11476427openalex-snapshot
Accelerating Enterprise Application Development Through AI-Enhanced Low-Code Platforms: An Empirical Analysis of Oracle APEX with Generative AI Integration
inferred← citeshttps://doi.org/10.1109/tce.2026.3657783openalex-snapshot
A Wi-Fi-Based Authentication Scheme for Voice-Enabled Large Language Model Consumer Electronics Devices
inferred← citeshttps://doi.org/10.1109/tdsc.2025.3620832openalex-snapshot
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
inferred← citeshttps://doi.org/10.1109/tifs.2026.3671126openalex-snapshot
A Fine-Tuning Data Recovery Attack on Generative Language Models via Backdooring
inferred← citeshttps://doi.org/10.1109/tnse.2026.3680460openalex-snapshot
Topology Linearization for Multi-Agent Systems Security: Mitigating Malicious Propagation via Path Decomposition
inferred← citeshttps://doi.org/10.1109/tnsm.2026.3724323openalex-snapshot
Correction Forest: A Misclassification Correction Model for Reducing the Total Error Rate of IIoT Network Intrusion Detection
inferred← citeshttps://doi.org/10.1109/wcnc65185.2026.11555516openalex-snapshot
Large Reasoning Models for Optimal Resource Management in Next Generation Wireless Networks
inferred← citeshttps://doi.org/10.1145/3712001openalex-snapshot
Security and Privacy Challenges of Large Language Models: A Survey
inferred← citeshttps://doi.org/10.1145/3773080openalex-snapshot
The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
inferred← citeshttps://doi.org/10.1145/3802927.3802956openalex-snapshot
PrivacyNotice: Pre-Interaction Minimization of User Disclosures in the LLM Application Ecosystem
inferred← citeshttps://doi.org/10.1145/3806007.3810957openalex-snapshot
A Case Study on the Impact of Anonymization Along the RAG Pipeline
inferred← citeshttps://doi.org/10.1177/1088467x261471261openalex-snapshot
Activation-based efficient routing for retrieval-augmented generation in LLMs
inferred← citeshttps://doi.org/10.1186/s42400-025-00522-xopenalex-snapshot
MTDecipher: robust encrypted malicious traffic detection via multi-task graph neural networks
inferred← citeshttps://doi.org/10.1365/s40702-026-01283-yopenalex-snapshot
Agentenbasierte Fahrgastinformationssysteme für den ÖPNV
inferred← citeshttps://doi.org/10.47134/jtsi.v3i2.6047openalex-snapshot
AdverShield-LLM: Adversarial Robustness Certification for IoT-Integrated Retrieval-Augmented Generation via Randomized Smoothing
inferred← citeshttps://doi.org/10.9728/dcs.2026.27.2.357openalex-snapshot
Fake News Detection Based on Lightweight Text Structural Cues
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.