LLM Defense Mechanisms

Ask about this topic

Momentum

32 papers in the last four weeks, up 256% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 258

All topics
CardsList

  1. A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

    Apr 17, 2026Zehao Lin, Xixuan Hao, Renyu Fu +5Large Language Model AgentsLLM Defense Mechanisms

    MemTensor · Shanghai Jiao Tong University

  2. DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering

    Feb 22, 2026Yiran Qiao, Yiren Lu, Yunlai Zhou +43D Gaussian3D Reconstruction

    Case Western Reserve University, Cleveland OH 44106, USA

  3. Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

    Feb 9, 2026Jiacheng Liu, Yaxin Luo, Jiacheng Cui +3CaptchaAgentic Benchmarks

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · MetaAgentX · University College London

  4. Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target Recognition

    Dec 31, 2025Yuchao Hou, Zixuan Zhang, Jie Wang +9Synthetic Aperture RadarFederated Learning

    Shanxi Normal University, Taiyuan, China · Guizhou University, Guiyang, China · Shanxi Key Laboratory of Cryptography and Data Security, School of Computer Science and Artificial Intelligence, Shanxi Normal University, Taiyuan 030031, China +15

  5. SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models

    Dec 20, 2025Scott ThorntonVulnerable CodeSecurity Evaluation

  6. MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS

    Nov 28, 2025Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +8LLM Defense MechanismsLinguistics

    Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240, China

  7. BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models

    Nov 24, 2025Juncheng Li, Yige Li, Hanxun Huang +5LLM Defense Mechanisms

    Fudan University · Singapore Management University · The University of Melbourne

  8. GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning

    Nov 14, 2025Ying Song, Balaji PalanisamyMembership Inference AttacksUnlearnable Examples

    University of Pittsburgh Pittsburgh, PA, USA

  9. "Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

    Nov 3, 2025Qin Zhou, Zhexin Zhang, Zhi Li +1Peer ReviewLLM Defense Mechanisms

    Institute of Information Engineering, CAS, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · The Conversational AI (CoAI) group, DCST, Tsinghua University

  10. Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

    Oct 18, 2025Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1Large Language Model AgentsLarge Language Model Safety

    University of California, Berkeley · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · International Institute of Information Technology, Hyderabad (IIIT Hyderabad)

  11. Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

    Oct 1, 2025Shoumik Saha, Jifan Chen, Sam Mayers +3Jailbreak AttacksSecurity Evaluation

    University of Maryland – College Park · AWS AI Labs · Meta Superintelligence Labs

  12. Adversarial Defense in Cybersecurity: A Systematic Review of GANs for Threat Detection and Mitigation

    Sep 24, 2025Tharcisse Ndayipfukamiye, Jianguo Ding, Doreen Sebastian Sarwatt +2Threat DetectionCybersecurity

    Department of Computer Science and Technology, University of Science and Technology Beijing · Department of Computer Science, Blekinge Institute of Technology

  13. Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs

    Aug 9, 2025Jinhwa Kim, Ian G. HarrisJailbreak AttacksLarge Language Models Fail

    Department of Computer Science University of California, Irvine

  14. CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection

    Apr 2, 2025Diego Cajaraville-Aboy, Marta Moure-Garrido, Carlos Beis-Penedo +5Threat DetectionFederated Learning

    atlanTTic Research Center – ICLAB – Universidade de Vigo, Vigo, 36310, Spain · Department of Telematic Engineering, Universidad Carlos III de Madrid, Spain

  15. Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots

    Dec 21, 2024Xuancun Lu, Zhengxian Huang, Xinfeng Li +3Large Language Model JailbreaksJailbreak Attacks

    Zhejiang University

  16. Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge

    Apr 8, 2024Weikai Lu, Ziqian Zeng, Jianwei Wang +5Large Language Model JailbreaksJailbreaks

    South China University of Technology, China · Pazhou Laboratory, China

  17. Builder, Defender, Breaker: Measurable Independence and Bounded Autonomy When Generative Models Build, Defend and Test Software

    Date pendingMohamed Chahine GhanemLLM Defense MechanismsCode Generation

    School of Computer Science and Mathematics, Keele University, Newcastle-under-Lyme, United Kingdom · Cybersecurity Institute, University of Liverpool, Liverpool, United Kingdom

  18. A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility

    Date pendingShikhar Shiromani, Leo RichterEvasionChain-of-Thought Reasoning

    Pivotal Research · University College London