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. Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy

    Jul 30, 2026Puning Zhao, Zhikun Zhang, Shaowei Wang +5Distributionally-Robust OptimizationPoisoning

    Shenzhen Campus of Sun Yat-sen University · Zhejiang University · Guangzhou University +2

  2. VETO: Towards Protecting Images From Frontier AI Editing

    Jul 29, 2026Jonas Grebe, Hossein Shakibania, Tobias Braun +2Ai-Generated Image DetectionLLM Defense Mechanisms

    TU Darmstadt & hessian.AI, Germany · Zuse School ELIZA

  3. InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

    Jul 29, 2026Jian Xiong, Wenbo Jiang, Zihan Wang +4HandwritingForgeries

    University of Electronic Science and Technology of China

  4. Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

    Jul 29, 2026Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4LLM Defense MechanismsAttack-Success Rate

    1Northeastern University

  5. RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning

    Jul 28, 2026Pushkal Kumar, Tucker Nielson, Tanish Kolhe +2Agentic Retrieval-Augmented Generation SystemsPoisoning

  6. I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models

    Jul 28, 2026Yimao Guo, Zuomin Qu, Wei LuDiffusion TransformersBlack-Box Adversarial Attacks

    School of Computer Science and Engineering, Sun Yat-sen University Ministry of Education Key Laboratory of Information Technology Guangdong Province Key Laboratory of Information Security Technology Guangzhou 510006, China · Guangdong Province Key Laboratory of Information Security Technology Guangzhou 510006, China · State Key Laboratory of HVDC, China Southern Power Grid Electric Power Research Institute

  7. Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

    Jul 28, 2026Abu Bakar SiddikCybersecurityModel Vulnerabilities

    Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh

  8. Hybrid Analysis for Secure MCP Tool Use in LLM Agents

    Jul 28, 2026Ping He, Yuexiang Xie, Yaliang Li +1Large Language Model SafetyLarge Language Model Agents

    Zhejiang University · Alibaba Group

  9. SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

    Jul 28, 2026Haowen Dai, Zonghao Ying, Wenfeng Li +10Information-Flow ControlMalicious Agents

    University of Nottingham Ningbo China · Beihang University · Shandong University +6

  10. When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs

    Jul 27, 2026Tong Zhang, Zexin Li, Simin Chen +1LLM Defense MechanismsLarge Language Models Fail

    Fudan University · University of California, Riverside · Columbia University

  11. Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening

    Jul 24, 2026Huy Q. NgoSecurityLLM Defense Mechanisms

    School of Computer and Mathematical Sciences, The University of Adelaide

  12. A Defense of the Quadratic Model

    Jul 23, 2026Alexandru Meterez, Pranav Ajit Nair, Depen Morwani +3Anisotropic Loss LandscapesLarge Language Model Training

    1Kempner Institute at Harvard University · †: Work done while at Harvard. · 2MIT

  13. Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous Racing

    Jul 23, 2026Yufei Xi, Yijie Liao, Tulga ErsalAutonomous RacingModel Predictive Control

    Department of Mechanical Engineering, College of Engineering, University of Michigan, Ann Arbor, MI, USA. · Department of Electrical Engineering and Computer Science, College of Engineering, University of Michigan, Ann Arbor, MI, USA. · School of Computing, National University of Singapore, Singapore.

  14. IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

    Jul 22, 2026Ankur Singh, Jinqiu Yang, Tse-Hsun ChenCoding AgentsVulnerable Code

    Concordia University Montr´eal, Canada

  15. Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

    Jul 22, 2026Yuxi Li, Zhibo Zhang, Kailong Wang +3Attacker Large Language ModelClean Label Backdoor Attack

    Huazhong University of Science and Technology China · Nanjing University of Aeronautics and Astronautics China · Nanyang Technological University Singapore

  16. CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

    Jul 21, 2026Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad +4Prompt-Injection DetectorsAutomatic Prompt Optimization

    University of British Columbia · 2Vector Institute · 3McMaster University +1

  17. The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI

    Jul 20, 2026Om Narayan, Ramkinker Singh, Praveen BaskarRealistic Threat ModelLLM Defense Mechanisms

    Department of Computer Science New York University New York, NY, USA · Carnegie Mellon University Pittsburgh, PA, USA · Independent Researcher Chicago, IL, USA

  18. Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

    Jul 20, 2026Yimeng Chen, Nathanaël Denis, Roberto Di Pietro +1Diverse AttacksLLM Defense Mechanisms

    Center of Excellence for Generative AI, King Abdullah University of Science and Technology · The Swiss AI Lab, IDSIA-USI/SUPSI

  19. Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models

    Jul 20, 2026Tuan Duong Trinh, Naveed Akhtar, Basim AzamLLM Defense MechanismsDouble-Edged Sword

    University of Melbourne Parkville, VIC, Australia

  20. Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models

    Jul 20, 2026Dongdong Yang, Deyue Zhang, Zhao Liu +5Adversarial PromptsJailbreak Success Rates

    AI Security Lab, Beijing, China · School of Artificial Intelligence, Beihang University, Beijing, China

  21. Salience Induction against Multi-Hop RAG Agents: Threat and Defense

    Jul 20, 2026Xingfu Zhou, Pengfei Wang, Yuan Zhou +2LLM Defense MechanismsMulti-Hop Reasoning

    National University of Defense Technology China

  22. How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

    Jul 19, 2026Yukai Zhou, Feiyang Lu, Xiaokai Mao +2Jailbreak AttacksJailbreaks

    ShanghaiTech University · Zhejiang University

  23. A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic

    Jul 19, 2026Khushnaseeb RoshanBlack-Box Adversarial AttacksIntrusion Detection

    Department of Computer Science, Aligarh Muslim University (AMU), Aligarh, INDIA

  24. SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models

    Jul 17, 2026Jinwen Xin, Xixiang LvLLM Defense MechanismsUtterances

    School of Cyber Engineering Xidian University Xi’an, China

  25. Large Audio Language Models for Spoofing-Aware Speaker Verification

    Jul 16, 2026Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir +3Automatic Speaker VerificationLarge Audio Language Models

    Applied AI Institute · MIRAI · AXXX, HSE +3

  26. Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learning

    Jul 9, 2026Zifan Zhang, Minghong Fang, Dianwei Chen +5PoisoningDigital Twins

    North Carolina State University, USA · University of Louisville, USA · University of Maryland, USA +2

  27. Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

    Jul 8, 2026Giulia Marchiori Pietrosanti, Giulio Rossolini, Giorgio ButtazzoModel-Agnostic DefenseVision Transformer

    Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Study, Italy

  28. ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN

    Jul 7, 2026Md Raihan Uddin, Fatemeh Lotfi, Tolunay Seyfi +1Clean Label Backdoor AttackModel-Agnostic Defense

    Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA

  29. Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

    Jul 7, 2026Mohammadreza RashidiModel Context ProtocolMetadata

    Department of Computer Science AI and Media Analysis Lab Berlin, Germany

  30. Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

    Jul 6, 2026Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu +1LLM Reasoning StrategiesLLM Defense Mechanisms

    The Pennsylvania State University, University Park, PA, USA

  31. Privacy-Preserving and Verifiable Approximate Distributed Coded Computing

    Jul 2, 2026Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga +1Privacy-Preserving Machine LearningFederated Learning

    Galician Research and Development Center in Advanced Telecommunications (GRADIANT) Estrada do Vilar, 56-58, Vigo, 36214, Spain · atlanTTic, Information & Computing Lab (ICLAB), Telecommunication Engineering School, Universidade de Vigo Vigo, 36310, Spain

  32. SoK: Attack and Defense Landscape of Mobile On-device AI Systems

    Jul 1, 2026Yujin Huang, Xin Zheng, Xingliang Yuan +1DeviceLLM Defense Mechanisms

    The University of Melbourne · RMIT University · Nanyang Technological University

  33. Embedding Inference Attack

    Jul 1, 2026Cedric Fitiavana Raelijohn, Sébastien Gambs, Jean-Francois RajotteRetrieval-Augmented Generation PipelinesText Embeddings

    Université du Québec à Montréal, Canada

  34. TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

    Jun 30, 2026Dariush Wahdany, Matthew Jagielski, Jesse C. Cresswell +2Privacy-Preserving Machine LearningMembership Inference Attacks

    CISPA · Anthropic · Layer 6 AI

  35. MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination

    Jun 30, 2026Xinlei Liu, Jichao Xie, Tao Hu +4Adversarial TrainingLLM Defense Mechanisms

    Information Engineering University, Zhengzhou, 450002, China · Key Laboratory of Cyberspace Security, Ministry of Education, Zhengzhou, 450002, China

  36. Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning

    Jun 29, 2026Antonio Marino, Esteban Restrepo, Soon-jo Chung +2Multi-Robot SystemsMulti-Agent Reinforcement Learning

    University of Cambridge · CNRS, Univ Rennes, Inria, IRISA · Division of Engineering and Applied Science, California Institute of Technology

  37. Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

    Jun 29, 2026Mitchell Hermon, Rahul Gupta, Weitong Ruan +2Prompt-Injection DetectorsLarge Language Model Safety

    University of Illinois Urbana-Champaign · 2Amazon

  38. Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

    Jun 29, 2026Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1Semantic CommunicationsWireless Communications

    Nexcepta, Gaithersburg, MD, USA · The Ohio State University, Columbus, OH, USA · University of Maryland, College Park, MD, USA

  39. Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing

    Jun 29, 2026Dvir Alsheich, Adar Peleg, Ben Hagag +3Semantic FirewallAttacker Large Language Model

    1Technion - Israel Institute of Technology · 2Carnegie Mellon University

  40. On the Vulnerability of Parameter-Level Defenses to Model Merging

    Jun 29, 2026Kuangpu Guo, Qingyan Zheng, Jian Liang +4Model-Agnostic DefenseLLM Defense Mechanisms

    University of Science and Technology of China · School of Artificial Intelligence, University of Chinese Academy of Sciences · NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences +1

  41. Theory of Continual Learning Against Data Poisoning Attacks

    Jun 29, 2026Yiting Hu, Lingjie DuanReplay-Based Continual LearningPoisoning

    Singapore University of Technology and Design, Singapore · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China.

  42. The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

    Jun 28, 2026Tuo Chen, Minjing Dong, Benlei Cui +2EncodersLLM Defense Mechanisms

    Southeast University · Ant Group · City University of Hong Kong +2

  43. Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense

    Jun 28, 2026Subhadip MitraInference-Time DefenseLLM Defense Mechanisms

    Independent Researcher

  44. FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

    Jun 27, 2026Aoying Zheng, Anqi Du, Zizhuang Deng +1Large Language Model BackbonesLLM Defense Mechanisms

    School of Cyber Science and Technology Shandong University · Suzhou Research Institute of Shandong University

  45. Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

    Jun 27, 2026Thomas Thebaud, Sonal Joshi, Henry Li +4PoisoningLLM Defense Mechanisms

    Center for Language and Speech Processing, Johns Hopkins University, USA · Faculty of Information Technology, Brno University of Technology, Czechia

  46. Agent-Native Immune System: Architecture, Taxonomy, and Engineering

    Jun 26, 2026Bo Shen, Lifeng Chang, Tianyuan Wei +7LLM Defense MechanismsAntimicrobial Peptide

    Novo Ordo for AI

  47. On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

    Jun 25, 2026Dewank Pant, Shruti Lohani, Avijit KumarPrompt-Injection DetectorsUntrusted Content

    Independent Researcher

  48. Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents

    Jun 25, 2026Praneeth Narisetty, Shiva Nagendra Babu Kore, Uday Kumar Reddy Kattamanchi +1Indirect Prompt InjectionLLM Defense Mechanisms

    LaunchSafe Research

  49. Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems

    Jun 24, 2026Balamurugan Palanisamy, G S S Chalapathi, Vikas Hassija +1Agentic Retrieval-Augmented Generation SystemsLarge Language Model Safety

    Department of Electrical and Electronics Engineering Birla Institute of Technology and Science, Pilani, Pilani Campus Vidya Vihar, Pilani, Rajasthan 333031, India · Department of Computer Engineering, KIIT University Bhubaneshwar, Odisha 751024, India · Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory Department of Computing and Information Systems The University of Melbourne, Melbourne, Australia

  50. What Does It Mean to Break a Distillation Defense?

    Jun 23, 2026Lena Libon, Pura Peetathawatchai, Michael Aerni +2Realistic Threat ModelLLM Defense Mechanisms

    ETH Zurich

  51. Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection

    Jun 23, 2026Gautier-Edouard Edouard FilardoQuantum Neural NetworksQubit

    CREOGN · Efrei Research Lab, Efrei Paris Panth´eon-Assas Universit´e, Villejuif, France

  52. Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

    Jun 18, 2026Reza Soosahabi, Vivek NamsaniLLM Defense MechanismsAttack-Success Rate

    Application & Threat Intelligence Research Center Keysight Technologies Inc., USA

  53. Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

    Jun 18, 2026Farhin Farhad Riya, Shahinul Hoque, Yingyuan Yang +2Cyber-Physical SystemPower Systems

    Department of Electrical Engineering and Computer Science, University of Tennessee · Department of Computer Science, The University of Illinois at Springfield · Department of Electrical and Computer Engineering, Clemson University, South Carolina

  54. When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

    Jun 18, 2026Kaiyue Yang, Yuyan Bu, Jingwei Yi +5Controlling Tool UseLarge Language Model Agents

    Institute of Information Engineering, Chinese Academy of Sciences · Beijing Academy of Artificial Intelligence · The Chinese University of Hong Kong +2

  55. Blame is easier than praise: Measuring off-ball defensive performance in football

    Jun 18, 2026Jonas Bischofberger, Runqing Ma, Pascal Bauer +2LLM Defense MechanismsGround Truth

    Centre for Sport Science and University Sports, University of Vienna, Vienna, Austria · Vienna Doctoral School of Pharmaceutical, Nutritional and Sport Sciences (VDS-PhaNuSpo), University of Vienna, Vienna, Austria · VfB Stuttgart 1893 AG, Stuttgart, Germany +2

  56. TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction

    Jun 17, 2026Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun +2PrivacyLeakage

    Dept. of Electrical Engineering, POSTECH · Grad. School of Artificial Intelligence, POSTECH · Grad. School of Metaverse, KAIST +1

  57. Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks

    Jun 16, 2026Aaditya PaiPrompt-Injection DetectorsLLM Defense Mechanisms

    Data Science Institute Columbia University

  58. MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense

    Jun 16, 2026Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan +5Adversarial TrainingLLM Defense Mechanisms

    Department of Computer Science, San Jos´e State University, San Jos´e, CA, USA · Department of Computer Engineering, San Jos´e State University, San Jos´e, CA, USA · Department of Applied Data Science, San Jos´e State University, San Jos´e, CA, USA +1

  59. Automated jailbreak attack targeting multiple defense strategies

    Jun 15, 2026Qi Wang, Chengcheng Wan, Weijia He +4Attacker Large Language ModelJailbreak Attacks

    East China Normal University Shanghai, China · East China Normal University, Shanghai Innovation Institute Shanghai, China · University of Southampton Southampton, England +2

  60. Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance

    Jun 15, 2026Dara Goldar, Geir Kjetil Ferkingstad Sandve, Martin JullumAnti-Money LaunderingInsurance

    Fremtind Insurance · University of Oslo · Norwegian Computing Center