LLM Security

LLM: Large Language Model

Ask about this topic

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

327 papers45 papers in the last four weeks, up 45% on the four weeks before. 0.3% of all new papers.

  1. Kolmogorov Complexity Bounds for LLM Steganography and a Perplexity-Based Detection Proxy

    Mar 23, 2026Andrii ShportkoKolmogorov ComplexityLanguage Model Steganography

    Northwestern University Evanston, IL

  2. Detection of adversarial intent in Human-AI teams using LLMs

    Mar 21, 2026Abed K. Musaffar, Ambuj Singh, Francesco BulloAI Agent SecurityAI Agent Monitoring

    Department of Mechanical Engineering, University of California at Santa Barbara · Department of Computer Science, University of California at Santa Barbara

  3. Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models

    Mar 20, 2026Wenjing Hong, Zhonghua Rong, Li Wang +5Jailbreak AttacksLLM Jailbreak Attacks

    School of Artificial Intelligence Shenzhen Univeristy, China · Brain-Inspired Technology Co.,Ltd, China · Department of Computer Science and Engineering Southern University of Science and Technology, China +1

  4. When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection

    Mar 19, 2026Georgios Alexopoulos, Nikolaos Alexopoulos, Diomidis Spinellis +1Automated Code ReviewAdversarial Attacks on LLMs

    University of Athens · National Infrastructures for Research and Technology · Athens University of Economics and Business +1

  5. Toward Reliable, Safe, and Secure LLMs for Scientific Applications

    Mar 18, 2026Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi MallickLLM SafetyAI Agent Safety

    Argonne National Laboratory, Lemont, 60439, USA

  6. MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)

    Mar 18, 2026Yi Ting Shen, Kentaroh Toyoda, Alex LeungMCP SecurityLLM Security

    Vulcan Research, AIFT

  7. Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework

    Mar 17, 2026Taiwo Onitiju, Iman VakiliniaLLM SecurityAdversarial Attacks on LLMs

    School of Computing, University of North Florida

  8. SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuit

    Mar 17, 2026Yibo Li, Qiongxiu LiGradient Inversion AttacksPrivacy Leakage in Language Models

    Politecnico di Milano / Italy · Aalborg University

  9. SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment

    Mar 17, 2026Zhouwei Zhai, Mengxiang Chen, Anmeng ZhangE-Commerce SearchKnowledge Augmentation for Language Models

    JD.com Beijing, China

  10. Resource Consumption Threats in Large Language Models

    Mar 17, 2026Yuanhe Zhang, Xinyue Wang, Zhican Chen +8LLM SecurityLLM Inference Efficiency

    Beijing University of Posts and Telecommunications · Hangzhou Dianzi University · Nanyang Technological University +1

  11. Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

    Mar 14, 2026Zijian Ling, Pingyi Hu, Xiuyong Gao +6Adversarial AttacksLLM Security

    School of Cyber Science and Engineering, Huazhong University of Science and Technology · State Key Laboratory of Internet Architecture, Tsinghua University · Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology +1

  12. Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment

    Mar 13, 2026Sihao DingLLM SecurityLLM Safety Alignment

    Mercedes-Benz Research & Development North America, USA

  13. SpectralGuard: Detecting Memory Collapse Attacks in State Space Models

    Mar 12, 2026Davi BonettoLLM SecurityState Space Models

    Independent Researcher

  14. CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks

    Mar 12, 2026Alexandre Le Mercier, Thomas Demeester, Chris DevelderLLM SecurityLanguage Model Robustness

    IDLab–T2K, Ghent University–imec

  15. Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems

    Mar 12, 2026Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner +2AI Agent SecurityLLM Security

    The University of Texas at Austin · Georgia Tech · Intel Labs +2

  16. Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms

    Mar 11, 2026Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1Secure Code GenerationCode Language Models

    Cognitive Security Technologies Fraunhofer Institute for Applied and Integrated Security Garching near Munich, Germany

  17. TOSSS: a CVE-based Software Security Benchmark for Large Language Models

    Mar 11, 2026Marc Damie, Murat Bilgehan Ertan, Domenico Essoussi +3LLM Safety BenchmarksSoftware Security

    Modat, The Hague, The Netherlands

  18. CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-Tenant LLM Serving Systems

    Mar 11, 2026Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri +1LLM SecurityPrefix Caching

    IMDEA Software Institute Universidad Politécnica de Madrid · IMDEA Software Institute

  19. FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

    Mar 10, 2026Yinpeng Wu, Yitong Chen, Lixiang Wang +3LLM ServingOn-Device Language Model Inference

    Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University

  20. Invisible Safety Threat: Malicious Finetuning for LLM via Steganography

    Mar 9, 2026Guangnian Wan, Xinyin Ma, Gongfan Fang +1Language Model SteganographyLLM Security

    National University of Singapore

  21. VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription

    Mar 8, 2026Sumit Ranjan, Sugandha Sharma, Ubaid Abbas +1LLM Security

    Emvo

  22. Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment

    Mar 8, 2026Neha Nagaraja, Hayretdin BahsiLLM SecurityCybersecurity

    School of Informatics, Computing, and Cyber Systems, Northern Arizona University, Flagstaff, USA · Department of Software Science, Tallinn University of Technology, Tallinn, Estonia

  23. Good-Enough LLM Obfuscation (GELO)

    Mar 5, 2026Anatoly Belikov, Ilya FedotovPrivacy-Preserving Language ModelsLLM Security

    SingularityNET Foundation, Baarerstrasse 141, Zug, 6300, Switzerland · Singularity Compute

  24. Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

    Mar 4, 2026Neha Nagaraja, Hayretdin BahsiLLM SecurityAI Agent Security

    School of Informatics, Computing, and Cyber Systems, Northern Arizona University, Flagstaff, USA · Department of Software Science, Tallinn University of Technology, Tallinn, Estonia

  25. DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

    Mar 2, 2026Xiaoyi Pang, Xuanyi Hao, Pengyu Liu +3LLM SecurityBackdoor Defense in LLMs

    The Hong Kong University of Science and Technology, Hong Kong · The State Key Laboratory of Blockchain and Data Security, Zhejiang University, P. R. China · School of Cyber Science and Technology, Zhejiang University, P. R. China

  26. Jailbreaking Embodied LLMs via Action-level Manipulation

    Mar 2, 2026Xinyu Huang, Qiang Yang, Leming Shen +2AI Agent SecurityLLM Security

    The Hong Kong Polytechnic University, Hong Kong SAR, China · University of Cambridge, Cambridge, United Kingdom

  27. Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs

    Feb 28, 2026Jingyuan Xie, Wenjie Wang, Ji Wu +1Adversarial Attacks on LLMsLLM Security

    Department of Electronics Engineering, Tsinghua University, Beijing, China · College of AI, Tsinghua University, Beijing, China · Beijing National Research Center for Information Science and Technology, Beijing, China

  28. A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

    Feb 26, 2026Usman Anwar, Julianna Piskorz, David D. Baek +6Language Model SteganographyLLM Security

    University of Cambridge · Massachusetts Institute of Technology · UK AI Safety Institute +3

  29. Evaluation of Audio Language Models for Fairness, Safety, and Security

    Feb 25, 2026Ranya Aloufi, Srishti Gupta, Soumya Shaw +2Audio-Language Model EvaluationAudio-Language Models

  30. Manifold of Failure: Behavioral Attraction Basins in Language Models

    Feb 25, 2026Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala +4LLM SecurityLLM Safety

    Amazon Web Services · Amazon Leo · Cisco +1