Exploitation

Ask about this topic

Momentum

10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 66

All topics
CardsList

  1. Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics

    Sep 30, 2026Songhua Yang, Ziyu Liu, Yuanwei Liu +5Diffusion-Based Vision-Language-ActionsAdversarial Examples

    School of Computer Science, Wuhan University. · School of Robotics, Wuhan University. · School of Power and Mechanical Engineering, Wuhan University.

  2. Alignment via Training Against Probes Without Losing Monitorability

    Sep 29, 2026Lena Libon, Alexander Panfilov, Ben Rank +3Safety AlignmentModel Activations

    ETH Zurich · ELLIS Institute Tübingen, MPI for Intelligent Systems, Tübingen AI Center

  3. Let the Neurons Die: Exploiting ReLU-Induced Model Degradation

    Sep 28, 2026Kexin Li, Wenjun Qiu, Joshua Abraham +2Rectified Linear Unit NetworksNeurons

    University of Toronto, Toronto, Ontario, Canada

  4. SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing

    Sep 28, 2026Zhiwei Chen, Tianchun Wang, Zhongtao Rao +3Strategic ReasoningLarge Language Model Agents

    The Hong Kong University of Science and Technology (Guangzhou) · Johns Hopkins University · Microsoft +2

  5. Evaluating Coding Agents on Kernel Exploit Generation

    Sep 22, 2026Junyoung Jang, Gwanhyun Lee, Hwiwon Lee +4ExploitationCoding Agents

    Independent Researcher · University of Illinois Urbana-Champaign · Ministry of National Defense, Republic of Korea

  6. Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

    Sep 17, 2026Sarah Radway, Andrew Cheng, Vijay Janapa Reddi +1ExploitationFingerprint

    Harvard University

  7. Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking

    Sep 14, 2026Arun Jose, Julian StastnyEmergent MisalignmentExploitation

    Astra Fellowship · Redwood Research

  8. Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code

    Sep 12, 2026Jessica Pourleyli, Maitreyee Das Urmi, Glaucia MeloProgram AnalysisVulnerable Code

    Toronto Metropolitan University Toronto, Canada

  9. Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks

    Sep 11, 2026Sebastiano Nordio, Michele LottoCybersecuritySmall Large Language Models

    Independent · University of Genoa, Via All’Opera Pia, 16145 Genoa, Italy

  10. VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

    Sep 7, 2026Jiahao Shi, Edward Tsien, Yifeng Di +10Model VulnerabilitiesExploitation

    Department of Computer Science, Purdue University · Red Hat

  11. BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks

    Aug 31, 2026Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs +3Agentic BenchmarksExploitation

    National University of Singapore · MIT · Vrije Universiteit Amsterdam +3

  12. LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles

    Aug 13, 2026Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1Program AnalysisExploitation

    Department of Civil, Construction & Environmental Engineering, The University of Alabama 2009 Smart Communities and Innovation Building (SCIB), 28 Kirkbride Lane, Tuscaloosa, AL 35487-0288 · Department of Computer Science, The University of Alabama 3017 Cyber Hall, 248 Kirkbride Lane, Tuscaloosa, AL 35487-0288

  13. Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes

    Aug 11, 2026Chen Xu, Zitian Guo, Chenyan XiongIncentivesCitations

    Carnegie Mellon University · University of California, San Diego

  14. Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

    Aug 8, 2026Ibne Farabi Shihab, Fariya AfrinProcess Reward ModelStress Testing

    Department of Computer Science, Iowa State University · Department of Computer Science, Kalinga Institute of Industrial Technology

  15. SafeDivertor: Faithful Divertor Heat Flux Reconstruction from Macroscopic Plasma State Signals via Time-Frequency Prior Exploitation

    Aug 6, 2026Hao Si, Zehua Chen, Qingquan Yang +8Heat DiffusionExploitation

    School of Computer Science and Technology, Anhui University, Hefei 230601, China · Department of Computer Science and Technology, Tsinghua University, Beijing, China · Institute of Plasma Physics, Chinese Academy of Sciences, Hefei 230601, China +1

  16. SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation

    Aug 6, 2026Yuru Feng, Yaoqi Chen, Beidi Zhao +7Self-Evolving Skill LibrariesSkills

    Microsoft · University of California, San Diego · University of Science and Technology of China +1

  17. MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models

    Aug 4, 2026Yu Ran, Wentao ZhaoGraphical User InterfaceAttack-Success Rate

    National University of Defense Technology

  18. Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation

    Jul 30, 2026Boning Li, Longbo HuangExploitationImperfect-Information Games

    IIIS, Tsinghua University

  19. The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play

    Jul 28, 2026Michael Macaulay, Harmony Bouabid, Guo Gen Ang +1Large Language Model SafetyCybersecurity

    WMG, University of Warwick, Coventry, United Kingdom

  20. Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI

    Jul 24, 2026Jiaqi Shao, Hanck Chen, Wei Zhang +2Agentic BenchmarksExploitation

    1Hunyuan Team, Tencent · 2The Hong Kong University of Science and Technology · 3Duke Kunshan University

  21. Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations

    Jul 15, 2026Rui Wang, Hongru Wang, Yi Chen +4TeacherExploration

    †The Chinese University of Hong Kong · ‡Tencent AI Lab

  22. Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation

    Jul 13, 2026Praneeth Narisetty, Shiva Nagendra Babu KoreExploitationSelf-Evolving Agents

    LaunchSafe

  23. Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

    Jul 8, 2026Florian Fuchs, Jessy Gosselin-Grant, Boris Skuin +5ExploitationOffline Reinforcement Learning

    Electronic Arts (EA)

  24. When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

    Jul 6, 2026Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2Autonomous AgentsDeliberation

    Carnegie Mellon University, Pittsburgh, USA · Jinesis AI Lab, Vector Institute and University of Toronto, Toronto, Canada · EuroSafeAI +1

  25. Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry

    Jul 4, 2026Weiyang Guo, Zesheng Shi, Longhui Zhang +3RetryingOffline Reinforcement Learning

    Harbin Institute of Technology, Shenzhen, China

  26. Safety Targeted Embedding Exploit via Refinement

    Jul 2, 2026Joshua Adrian CahyonoMultilingual SafetyLarge Language Model Safety

    Nanyang Technological University, Singapore.

  27. Projected Exploitability Descent for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games

    Jun 28, 2026Sam GanzfriedNash EquilibriumImperfect-Information Games

    Ganzfried Research, Cornell University

  28. CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?

    Jun 24, 2026Jintao Huang, Fengqing Jiang, Radha Poovendran +1Smart ContractsModel Vulnerabilities

    1The Ohio State University · University of Washington

  29. Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing

    Jun 24, 2026Liwei Yu, Shuo Li, Ming Zhou +2Penetration TestingExploitation

    University of Science and Technology of China, Hefei, China · Nanjing University of Science and Technology, Nanjing, China · Research Institute, Runjian Co., Ltd, China +1

  30. Execution-bound advisory automation for agentic AI: a reproducible AIBOM-driven CSAF-VEX framework

    Jun 16, 2026Petar Radanliev, Omar Santos, Carsten Maple +1Security EvaluationRuntime Enforcement

    Department of Computer Sciences, University of Oxford, Wolfson Building, Parks Rd, Oxford OX1 3QG · The Alan Turing Institute, British Library, 96 Euston Rd., London NW1 2DB · Cisco Systems, RTP, North Carolina, United States +2

  31. Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

    Jun 13, 2026Yiwei Chen, Lichi Li, Kai Cheung +2Model VulnerabilitiesExploitation

    Cisco Systems, Inc., San Francisco, CA, USA · Michigan State University, East Lansing, MI, USA

  32. Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

    Jun 8, 2026Mohammad Beigi, Ming Jin, Lifu HuangExploitation

    1UC Davis · 2Virginia Tech

  33. Cheap Reward Hacking Detection

    Jun 8, 2026Iván Belenky, Joaquín Itria, Steven JohnsExploitation

    Tamarillo

  34. VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

    Jun 6, 2026Harshil Patel, Kunal PaiModel Context ProtocolExploitation

    Department of Computer Science, University of California, Davis, CA, USA.

  35. FORGE: Multi-Agent Graduated Exploitation and Detection Engineering

    Jun 2, 2026Farooq ShaikhCommon Vulnerabilities And ExposureModel Vulnerabilities

    Dynatrace, Vienna, Austria

  36. Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits

    Jun 1, 2026Pu Wang, Yao-Xiang DingExploitationUnified Framework

    State Key Lab of CAD&CG, Zhejiang University

  37. Medication-Aware Financial Exploitation Detection for Alzheimer's Patients Using Edge-Aware Interaction Risk Modeling

    May 30, 2026Farzana Akter, Lisan Al Amin, Rakib Hossain +2AlzheimerMedication Leaflet

    Cognitive Links LLC, Maryland, USA · University of Maryland, College Park, USA

  38. When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

    May 30, 2026Su Wang, Pin Qian, Yihang Chen +6SkillsExploitation

    Carnegie Mellon University · Georgia Institute of Technology · University of Glasgow +2

  39. unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning

    May 27, 2026Geoffrey Bradway, Roger Creus Castanyer, Lorenz Wolf +3RobotwinExploitation

    Vmax

  40. Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

    May 24, 2026Wenlong Deng, Jiaji Huang, Kaan Ozkara +4Reward GradientsExploitation

    University of British Columbia · Vector Institute · Amazon

  41. Real-Time Auto-Optimization in Unknown Environments via Structure-Exploiting Dual Control for Exploration and Exploitation

    May 21, 2026Shiying Dong, Haoyang Yang, Qiwei Liu +1Optimal ControlOptimization Modeling

    Department of Aeronautical and Aviation Engineering and Research Centre for Low Altitude Economy (RCLAE), the Hong Kong Polytechnic University, Hong Kong, China

  42. Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

    May 20, 2026Amit Roth, Ankur Samanta, Matan Halevy +2Adversarial EvaluationExploitation

    1Tel Aviv University · 2Columbia University · 3Taso Labs

  43. Hallucination as Exploit: Evidence-Carrying Multimodal Agents

    May 18, 2026Guijia Zhang, Hao Zheng, Harry YangMultimodal AgentsReference-Guided Multimodal In-Context Verification

    1Shenzhen University · 2HKUST

  44. When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack

    May 17, 2026Zehan Sun, Dingfan Chen, Songze LiAttacker Large Language ModelLarge Language Models Fail

    1Southeast · 2Max Planck Institute for Intelligent Systems

  45. Imperfect World Models are Exploitable

    May 15, 2026Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel +2ExploitationWorld Models

    University of Edinburgh · Stanford University

  46. ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

    May 13, 2026Seunghyun Lee, David BrumleyExploitationVulnerable Code

    Carnegie Mellon University · Pittsburgh, PA 15213 · Carnegie Mellon University and Bugcrowd +1

  47. Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing

    May 13, 2026Daniel Fernández-González, Cristina Outeiriño CidTransformer EncoderSequence Modeling

    Universidade de Vigo, Departamento de Informática, Campus As Lagoas s/n, Ourense, 32004,, Spain

  48. Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution

    May 11, 2026Neil Fendley, Zhengyu Liu, Aonan Guan +2Agentic WorkflowsHijacking

    Johns Hopkins University Maryland, USA · Wyze Labs Washington, USA

  49. ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

    May 11, 2026Zhun Wang, Nico Schiller, Hongwei Li +13ExploitationVulnerable Code

    1UC Berkeley · 2Max Planck Institute for Security and Privacy · 3UC Santa Barbara +4

  50. Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust

    May 11, 2026Shijun Lei, Quang Nguyen, Swapneel S Mehta +7Multi-Agent SimulationsPersonalized Large Language Model Agents

    Northwestern Polytechnical University · Boston University · Fudan University +3

  51. Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models

    May 10, 2026Cameron Berg, Roshni LullaDeceptionLarge Language Model Bias

    1Reciprocal Research · 2Brain & Creativity Institute, University of Southern California

  52. Position: AI Security Policy Should Target Systems, Not Models

    May 10, 2026Michael A. Riegler, Inga StrümkeExploitationArtificial Intelligence Risk

    AI Safety Department SimulaMet and OsloMet Oslo, Norway · Department of Computer Science NTNU Trondheim, Norway

  53. AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play

    May 9, 2026Vlad Murgoci, Matthijs Spaan, Yaniv OrenPokerImperfect-Information Games

    Delft University of Technology · CD Delft, The Netherlands · Department of Intelligent Systems

  54. Drain-Vortex Optimization: A Population-Based Metaheuristic Inspired by Multi-Drain Free-Vortex Flow

    May 9, 2026Mohsen Omidi, Brian VaughanMetaheuristicsBasin

    Technological University Dublin, Grangegorman Lower, Dublin, D07 C972, Ireland

  55. Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

    May 7, 2026Nan Jia, Haojin Yang, Xing Ma +6Efficient On-Policy DistillationPolicy Gradient

    Huazhong University of Science and Technology · Peking University · Meituan

  56. MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents

    May 5, 2026Jonathan Steinberg, Oren GalVulnerable CodeCoding Agents

    Swarms & AI Lab (SAIL), University of Haifa

  57. APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks

    May 4, 2026Adel ElZemity, Budi Arief, Shujun Li +6Penetration TestingRemediation

    University of Kent, Canterbury, United Kingdom · University of Bristol, United Kingdom

  58. Towards Understanding Specification Gaming in Reasoning Models

    May 4, 2026Kei Nishimura-Gasparian, Robert McCarthy, David LindnerLarge Reasoning ModelsLarge Language Model Agents

    1MATS · University College London, London, UK · 3Google Deep- Mind.

  59. Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

    May 3, 2026Kunvar ThamanLarge Language Model AgentsExploitation

    Independent Researcher

  60. Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

    May 1, 2026Tung-Ling Li, Hongliang Liu, Yuhao WuLarge Language Model SafetyLarge Language Model Alignment

    Palo Alto Networks