LLM Security

LLM: Large Language Model

Overview

LLM security examines how models and the systems around them can be manipulated, made to leak information, or induced to take unsafe actions. Attacks include prompt injection and jailbreaks, poisoned training data and backdoors, model extraction, side channels in shared serving systems, and vulnerabilities in generated code or tool-using agents. Defenses range from safer training and fine-tuning to runtime detectors, access controls, secure serving, and application-level isolation; evaluations increasingly use adaptive attacks and realistic agent, coding, and deployment benchmarks. A central tension is that model-level safeguards can fail under new inputs or system interactions, while stronger controls may reduce utility, privacy, or efficiency, making end-to-end testing and clear threat models essential.

Latest papers

CardsList

344 papers26 papers in the last four weeks, down 38% on the four weeks before. 0.2% of all new papers.

  1. Network-Exposed Configuration Attacks on LLM-Controlled Social Robots

    Nov 17, 2026Stanley Akingbola, Ugbede Ibrahim, Yan Lin Aung +2CybersecurityAI Agent Security

  2. When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

    Nov 16, 2026Zeynab Anbiaee, Sajjad Dadkhah, Ali A. GhorbaniLLM SecurityTool Selection for Language Model Agents

  3. Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs

    Nov 12, 2026Gautam Galada, Supreeth Shastri, Sagnik Ray ChoudhuryLLM SecurityPrivacy Leakage in Language Models

  4. One Fabrication Is Enough: A Fake News Article Changes the Forecasts of LLM Forecasting Systems

    Nov 11, 2026Zeyu Zhang, Bradly C. StadieRAG Poisoning AttacksAdversarial Attacks on LLMs

  5. Chatter Attack: Resource Consumption Attack for Large Language Models

    Nov 8, 2026Yibo Miao, Yichuan Cao, Xiao-Shan Gao +1Adversarial Attacks on LLMsLLM Security

  6. Safety Is Π1Π_1, Provability Is Σ1Σ_1: One Framework for the Hugging Face Breach and OpenAI's Mathematical Proofs

    Nov 6, 2026Jinho Kang, Jinsook KimLLM SecurityDeductive Reasoning in Language Models

  7. Alignment Investigation of Mythos 5's behaviour in UK AISI's July 2026 Security Incident

    Nov 5, 2026Olli Järviniemi, Alexandra Souly, Abby D'Cruz +3LLM Safety AlignmentLLM Security

  8. A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code

    Nov 4, 2026Jiongchi Yu, Keke Lian, Junqing Wang +5LLM Code GenerationLLM Security

  9. JevBreak: Your Model, Their Decision

    Nov 2, 2026Nitin Aravind Birur, Divyanshu Kumar, Sahil Agarwal +1Adversarial AttacksAdversarial Text Attacks

  10. The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents

    Nov 2, 2026Geyuan Wang, Shunyu Liu, Siyuan Liang +2Adversarial AttacksAI Agent Security

  11. Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents

    Oct 29, 2026Georgios Syros, Blake Bullwinkel, Alina Oprea +4LLM Backdoor AttacksBackdoor Attacks

  12. InferD: A Honeypot Framework for AI Inference Infrastructure

    Oct 29, 2026Hicham Hammouchi, Gabriele LenziniAI Agent SecurityLLM Security

  13. Discovering Jailbreaks via Curriculum of Models

    Oct 28, 2026Michał Burzyński, Noah T. Rossi, Shomit Basu +1LLM SecurityLLM Jailbreak Attacks

  14. Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

    Oct 27, 2026Igor Shilov, Xiaoxue Yang, Alexander Panfilov +6LLM SecurityPrompt Injection Defense

  15. Detecting and Mitigating Query-Based System Prompt Leakage Attacks

    Oct 26, 2026Tushar Nayan, Pratik Poudel, Qian Lou +3LLM SecurityPrivacy Leakage in Language Models

  16. Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

    Oct 26, 2026Jiayue Pu, Ang Gao, Jinyi Bai +9Recursive Self-ImprovementLanguage Model Self-Improvement

  17. TrustJev: Separating Policy Authority from Untrusted Evidence in LLM-Based Decisions

    Oct 26, 2026Zhiwei Xu, Xuyang Liu, Xiaolin Peng +8LLM Decision-MakingLLM Security

  18. All-in-One: A Composable Attack on LLM Transformations

    Oct 23, 2026Xiaohua Zhan, Kazuki Egashira, Robin Staab +2LLM SecurityLLM Backdoor Attacks

  19. Amplifying Latency and Cost of LLM Inference via Rowhammer Attack

    Oct 22, 2026Mrityunjay Shukla, Shubham Roy, Biswabandan PandaLLM SecurityLLM Inference Efficiency

  20. Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts

    Oct 20, 2026Devansh Srivastav, David Pape, Samira Abedini +1LLM SecurityPrivacy Leakage in Language Models

  21. SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code

    Oct 19, 2026Mirza Masfiqur Rahman, MD Ajwad Akil, Imtiaz Karim +3LLM SecuritySoftware Vulnerability Detection

  22. MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language Models

    Oct 19, 2026Zhengao Li, Chuxu Zhang, Yushun DongKnowledge Augmentation for Language ModelsLLM Training

  23. BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition

    Oct 15, 2026Zhiyuan Wang, Yuezhi Zhou, Ziqi Zhang +3LLM SecurityOn-Device Language Model Inference