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. Defensive Sufficiency in a Stackelberg Model of AI Security

    Oct 7, 2026Subhabrata Majumdar, Rajlakshmi ChavanLLM Defense Mechanisms

    Indian Institute of Management Bangalore

  2. Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

    Oct 6, 2026Shaswata Mitra, Raj Patel, Subash Neupane +3LLM Defense Mechanisms

    Department of Computer Science The University of Alabama, Tuscaloosa, USA

  3. Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning

    Oct 1, 2026Meghana Sunil, Shravya V, Shravan Venkatraman +1Retrieval-Augmented Generation PipelinesInteractivity

    School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India. · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.

  4. False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift

    Oct 1, 2026Amit Singh Bhatti, Vishal VaddinaLarge Language Model SafetyDistribution Shifts

    Quantiphi Analytics

  5. MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs

    Oct 1, 2026Boyang Li, Bingyu Shen, Weihao Hong +6Large Language Model QuantizationJailbreak Success Rates

    Department of Computer Science, Kean University, 1000 Morris Ave, Union, 07083, NJ, USA · Department of Computer Science and Engineering, University of Notre Dame, 257 Fitzpatrick Hall of Engineering, Notre Dame, 46556, IN, USA · McGill University, 845 Sherbrooke Street, Montréal, H3A 0G4, Québec, Canada +2

  6. Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

    Sep 30, 2026Sachi Shome, William EiersFederated LearningPoisoning

    Stevens Institute of Technology

  7. Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning

    Sep 29, 2026Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2Model-Agnostic DefenseLarge Language Model Safety

    University of Louisville Louisville, Kentucky, USA

  8. DecoyTrace: Toxic Decoys for Active Defense in Decentralized Federated Learning

    Sep 28, 2026Pedro Beltrán-López, Enrique Tomás Martínez Beltrán, Pantaleone Nespoli +2Federated LearningModel-Agnostic Defense

    Department of Information and Communication Engineering, University of Murcia, Murcia, 30100, Spain

  9. Distillation Defenses Easily Break After Reinforcement Learning

    Sep 28, 2026Shidan Javaheri, Alexander Panfilov, Oliver Britton +2Probe-Logit DistillationLLM Defense Mechanisms

    University of Oxford · ELLIS Institute Tübingen & MPI for Intelligent Systems

  10. SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents

    Sep 28, 2026Xinjie Shen, Junran Wang, Rongzhe Wei +1LLM Defense MechanismsIncomplete Evidence

    Georgia Institute of Technology

  11. Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning

    Sep 28, 2026Zihan Zhang, Shuangjie Yao, Zesen Liu +8PoisoningAttacker Large Language Model

    The Hong Kong University of Science and Technology · Tsinghua University

  12. A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8

    Sep 27, 2026Basil Sajid Shaikh, Hajar HomayouniPhishingFraud Detection

    Independent Researcher Seattle, WA, USA · Associate Professor, Dept. of Computer Science San Diego State University San Diego, CA

  13. LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation

    Sep 27, 2026Jie Wang, Yanbo Sun, Zheng Yan +2AI TrustworthinessLog-Ratio-Based Gaussian Trust Weight

    State Key Laboratory of Integrated Services Networks, School of Cyber Engineering, Xidian University · Hangzhou Institute of Technology, Xidian University · Department of Computer Science, Purdue University

  14. ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models

    Sep 27, 2026Zhongjian Zhang, Xiao Wang, Busheng Zhang +5Zero-Shot RobustnessLLM Defense Mechanisms

    Beijing University of Posts and Telecommunications · Beihang University · Tsinghua University +2

  15. AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks

    Sep 24, 2026Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen +2Large Language Model JailbreaksRefusals

    National Taiwan University

  16. Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks

    Sep 23, 2026Ewelina Gajewska, Katarzyna Budzynska, Jaroslaw ChudziakLarge Language Model DecisionsArgumentation Frameworks

    Warsaw University of Technology

  17. Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents

    Sep 23, 2026Jinqian Zhang, Haojun Xia, Shujiang Wu +4LLM Defense Mechanisms

    Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Beihang University +1

  18. Toward Responsible AI-Augmented Cyber Defense: Pattern Recognition, Defense-in-Depth, and the Case for Human-AI Collaboration

    Sep 22, 2026Mustafa S. Aljumaily, Hayder Kareem Abed, Nawar S. AlseelawiHuman-Ai CollaborationLLM Defense Mechanisms

    Research and Development (R&D) Department, Daw Alfada Company, Baghdad, Iraq · CEO, Daw Alfada Company, Baghdad, Iraq · University of Misan, Maysan, Iraq

  19. Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy

    Sep 21, 2026Ruichang Zhang, Mustafa A. MustafaMembership Inference AttacksLLM Defense Mechanisms

    Department of Computer Science, The University of Manchester, Manchester, UK · COSIC, KU Leuven, Leuven, Belgium

  20. Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs

    Sep 15, 2026Kisu Yang, Yoonna Jang, Heuiseok LimLLM Defense MechanismsEncoders

    1VAIV Company · 2Hanwha Aerospace · 3Korea University

  21. Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

    Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia SmithLLM Defense MechanismsWhite-Box Spectral-Subspace-Guided Attack

    Carnegie Mellon University

  22. Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

    Sep 14, 2026Xiaoyan Li, Yunli WangAttacker Large Language ModelLLM Defense Mechanisms

    Department of Computer Science University of Toronto Toronto, Ontario, Canada · Digital Technologies Research Centre National Research Council Canada Ottawa, Ontario, Canada

  23. RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution

    Sep 14, 2026Xingyu Lyu, Jiayimei Wang, Jianfeng He +3PrivacyLLM Defense Mechanisms

    University of Massachusetts Lowell, Lowell, MA 01854, USA · City University of Hong Kong, Kowloon, Hong Kong SAR, 999077, China · Virginia Tech, Blacksburg, VA 24061, USA +2

  24. SALUTE: Benchmarking and Adapting LLMs for the Defense Domain

    Sep 14, 2026Hyeongcheol Park, Sumin In, Suyeon Myeong +5Large Language Model AdaptationLLM Defense Mechanisms

    Korea University, Republic of Korea · Sungkyunkwan University, Republic of Korea · Hanwha Systems, Republic of Korea

  25. PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

    Sep 14, 2026Yusuf Khalid Shire, Sang-Chul KimPrompt-Injection DetectorsModel-Agnostic Defense

    Department of Software Convergence, Kookmin University, Seoul, Republic of Korea

  26. Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning

    Sep 14, 2026Ting Xu, Henry LeungFederated LearningEquilibrium

    Department of Biomedical Engineering University of Calgary Calgary, Canada

  27. Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks

    Sep 12, 2026Guy Frankovits, Lior Yasur, Fred M. Grabovski +1Deepfake DetectionAuthenticity

    Ben-Gurion University, 1 Ben-Gurion Ave., Beersheba 8410501, Israel

  28. Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions

    Sep 12, 2026Dieuwertje Alblas, Alma M. Liezenga, Jan Erik van Woerden +3LLM Defense MechanismsReal-World

    Intelligent Imaging, Defense, Safety & Security, TNO, The Hague, The Netherlands

  29. Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

    Sep 12, 2026Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros +3Indirect Prompt InjectionCyber Threat Intelligence

    Aristotle University of Thessaloniki, Greece · Clone Systems, Cyprus

  30. CMNIE: An Information Extraction Benchmark for Chinese Military News

    Sep 11, 2026Yan Yu, Mengna Zhu, Zhenyu Song +3Relation ExtractionHeadlines

    Laboratory for Big Data and Decision, National University of Defense Technology, Changsha, China

  31. Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

    Sep 9, 2026Jing Guan, Yachao Yang, Zhaoliang Liu +3Model-Agnostic DefenseLLM Defense Mechanisms

    JIUTIAN Research, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China

  32. Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?

    Sep 8, 2026Bangshuo Zhu, Wei Song, Yuxin Cao +4LLM Defense MechanismsFrame Rate

    School of Computer Science and Engineering, University of New South Wales, New South Wales 2052, Australia · School of Information and Communication Technology, Griffith University, Queensland 4111, Australia · School of Computing, National University of Singapore, Singapore 117417, Singapore +2

  33. Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models

    Sep 8, 2026Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang +3Large Reasoning ModelsSafety Alignment

    Shanghai University of Engineering Science · The Hong Kong University of Science and Technology · A * STAR

  34. CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement

    Sep 7, 2026Boyang Zhang, Qingxin Xiao, Lingwei Dang +1Indirect Prompt InjectionLLM Defense Mechanisms

    School of Software Engineering, South China University of Technology

  35. Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents

    Sep 1, 2026Xiaofang Yang, Ziqi Miao, Dianbo Sui +2Runtime Safety FilteringMalicious Agents

    Shanghai Artificial Intelligence Laboratory · Harbin Institute of Technology, Weihai

  36. Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

    Aug 30, 2026Wujie Xiong, Rabimba Karanjai, Yang Lu +2LLM Defense MechanismsLarge Language Model Agents

    Kent State Univeristy · PayPal AI Labs · University of Houston

  37. Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents

    Aug 30, 2026Timothy Kassis, Vinayak Agarwal, Yuhuan He +2Reusable Agent SkillsScientific Workflows

    K-Dense, Inc.

  38. Defensive Boosting for Online Probabilistic Forecasting

    Aug 13, 2026Georgy Noarov, Aaron RothProbabilistic ForecastingLearning-Augmented Algorithms

  39. QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing

    Aug 13, 2026Shubin Lu, Jiaqi Yin, Yihao HuangLLM Defense Mechanisms

    School of Software, Northwestern Polytechnical University, Xi’an, China · Software Engineering Institute, East China Normal University, Shanghai, China

  40. SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense

    Aug 11, 2026Siyuan Liang, Yupeng Qiu, Junfeng Fang +3Text-To-Video Generation ModelJailbreak Success Rates

    Nanyang Technological University · National University of Singapore

  41. Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn Interaction

    Aug 10, 2026Yuqiao Xu, Osama Zafar, Alexander Nemecek +1Attacker Large Language ModelLLM Defense Mechanisms

    Case Western Reserve University

  42. Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

    Aug 10, 2026Hongli Shen, Shaopeng Fu, Qinbo Zhang +2Safety AlignmentJailbreak Attacks

    1King Abdullah University of Science and Technology · 2Stony Brook University

  43. Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation

    Aug 10, 2026Yanhang Li, Zhichao Fan, Zexin ZhuangModel AuditingLLM Defense Mechanisms

    Northeastern University · University of Illinois Urbana-Champaign · Southern Methodist University

  44. Robust Reputation-Driven Crowdsourced Federated Learning

    Aug 9, 2026Mouhamed Amine Bouchiha, Gregory BlancFederated LearningLog-Ratio-Based Gaussian Trust Weight

    SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris

  45. LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

    Aug 7, 2026Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1LLM Defense Mechanisms

    Michigan Technological University · Miami University · Lehigh University

  46. Improving Interoperability among Defence and National Security Ontologies: Analysis and Evaluation Tasks

    Aug 6, 2026Jonathon Dilworth, Pedro Giesteira Cotovio, David Herron +4OntologyInteroperability

    City St George’s, University of London, London, UK · LASIGE, Faculdade de Ciências, Universidade de Lisboa, Portugal · Defence Science and Technology Laboratory, UK +1

  47. Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots

    Aug 6, 2026S. M . Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, W. K. R. Sachinthana +1Vlm-To-Vla Capability TransferIndirect Prompt Injection

    Engineering Product Development Pillar · Singapore University of Technology and Design · Somapah Rd, Singapore 487372

  48. Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks

    Aug 6, 2026Chandan Hegde, Mukundh R ReddyIntrusion DetectionLLM Defense Mechanisms

  49. When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

    Aug 4, 2026Yongli Xiang, Zhifang Zhang, Bojun Yang +4Persona ConsistencyPrivacy

    1Sydney AI Centre, The University of Sydney · University of Queensland · 3Southeast University +1

  50. SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

    Aug 4, 2026Sungwon Cho, Kwanghyun Ko, Myungjoo KangSingular Value DecompositionLLM Defense Mechanisms

    Interdisciplinary Program in Artificial Intelligence Seoul National University · Interdisciplinary Program in Computational Science and Technology Seoul National University · Department of Mathematical Sciences Seoul National University

  51. Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining

    Aug 4, 2026Bangjie Sun, Nayoung Kim, Mun Choon Chan +1Locality-Sensitive HashingWhite-Box Spectral-Subspace-Guided Attack

    National University of Singapore (NUS) · Korea Advanced Institute of Science and Technology (KAIST)

  52. Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

    Aug 3, 2026Jia-Chen Zhang, Ze-Yu Zhang, Kai-Wei ZhangIndirect Prompt InjectionAdversarial Robustness

    1East China Normal University · 2Shanghai Jiao Tong University · 3Shanghai AI Laboratory

  53. S3S^3: Improving Agent Safety through Multi-Stage Defense

    Aug 3, 2026Zibo Xiao, Haoyu Wang, Jun SunAgentic WorkflowsLLM Defense Mechanisms

    Singapore Management University

  54. ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models

    Aug 2, 2026Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi +2Recent Vision-Language ModelsLLM Defense Mechanisms

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE · Khalifa University, UAE · University of Western Australia, Australia +1

  55. Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

    Aug 2, 2026Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2Jailbreak AttacksLLM Defense Mechanisms

  56. Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

    Aug 1, 2026Faisal Haque Bappy, Tahrim Hossain, Tarannum Shaila Zaman +3Attacker Large Language ModelMulti-Agent Large Language Model Systems

    University of Maryland Baltimore County, MD, USA · Kent State University, OH, USA · Tennessee State University, TN, USA

  57. ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation

    Jul 31, 2026Gaetano Perrone, Simon Pietro RomanoMachine-Generated Text DetectionLarge Language Model Benchmarks

    Department of Electrical Engineering and Information Technology, University of Napoli Federico II, Via Claudio 21, Naples, 80125, Italy

  58. Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

    Jul 31, 2026Weiyi He, Yuping Lin, Jiliang Tang +1Adversarial TrainingModel Fine-Tuning

    Michigan State University

  59. TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

    Jul 30, 2026Cheng WeiModel-Agnostic DefensePrivacy-Preserving Machine Learning

    Honor Device Co., Ltd., Shenzhen, China

  60. A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models

    Jul 30, 2026Xiangyu Yin, Tora Bodin, Rohan Menon +1Inference-Time DefenseLarge Language Model Jailbreaks

    Chalmers University of Technology, Gothenburg, Sweden · Carl von Ossietzky University of Oldenburg, Oldenburg, Germany