Malicious Agents

Ask about this topic

Momentum

11 papers in the last four weeks, up 38% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 103

All topics
CardsList

  1. Before Agent Tells The Lie: Has Deception Already Been Represented?

    Oct 5, 2026Xinling Li, Dadi Guo, Qingyu Liu +5DeceptionArtificial Intelligence Detection

    South China University of Technology · The Hong Kong University of Science and Technology · Shanghai Artificial Intelligence Laboratory +1

  2. Runaway Reaction: When Benign Skills Compose into Malicious Behavior

    Oct 5, 2026Zunlong Zhou, Ziyuan Yang, Mengyu Sun +1Malicious Agents

    Sichuan University

  3. Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents

    Sep 30, 2026Tobias Kaisar, Aritra DharMalicious AgentsAttacker Large Language Model

    Computing System Labs, Huawei Research Zurich

  4. ActionGuard: Tool Call Authorization under Poisoned Skills

    Sep 30, 2026Jihun Han, Yejin Jang, Byung Il Kwak +1Tool InvocationAuthorization

    Korea University Republic of Korea

  5. Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents

    Sep 30, 2026Wenxin Wu, Lingyong Yan, Lei Sha +2PoisoningMalicious Agents

    Beihang University · Baidu Inc · Wilfrid Laurier University

  6. MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate

    Sep 30, 2026Jiaming Zhang, Yuwan Liu, Yue Huang +1Multi-Agent DebateReputation

    Tsinghua University

  7. Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

    Sep 30, 2026Jiaqing Li, Shide Zhou, Zhibo Zhang +3Large Language Model UnlearningLarge Language Model Safety

    Huazhong University of Science and Technology · Hubei University

  8. SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs

    Sep 29, 2026Haoran Ou, Gelei Deng, Xuanye Zhang +3Malicious AgentsSkills

    Nanyang Technological University

  9. Quantization Enables Private Dense Retrieval against Malicious Service Providers

    Sep 28, 2026Louis Tremblay Thibault, Sofiane Azogagh, Marc-Olivier Killijian +1Retrieval LayerPrivacy

    École de technologie supérieure and Mila · Eurecom · Université du Québec à Montréal

  10. The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning

    Sep 27, 2026Sae Furukawa, Alina OpreaModel Fine-TuningPoisoning

    Khoury College of Computer Sciences, Northeastern University

  11. Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling

    Sep 17, 2026Bijied Brahimi, Vincent Cohadon, Gabriel Glazman +3MalwareMalicious Agents

    Université Paris Cité, Paris, France · Institut Polytechnique de Paris, Télécom Paris, Palaiseau, France

  12. Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures

    Sep 14, 2026Danny Wood, James StringerAttacker Large Language ModelSteganography

    Fuzzy Labs

  13. AI Persuasion as a Threat to Human Control

    Sep 13, 2026Joshua Levy, Mick Yang, Kellin PelrinePersuasionArtificial Intelligence Safety

  14. A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors

    Sep 3, 2026Pengxun Li, Litian Zhang, Jianwei Hou +4Malicious AgentsArtificial Intelligence Agents

    Beijing University of Posts and Telecommunications · Data and Technology Support Center of the Cyberspace Administration of China · Beihang University +1

  15. 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

  16. EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

    Aug 31, 2026Doyun Kim, Chanwoo Kim, Sugyeong Eo +2Self-Evolving AgentsMalicious Agents

    Soongsil University · Yonsei University · Jeju National University

  17. SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents

    Aug 22, 2026Yuanjin Zheng, Jingbang ChenMalicious AgentsAttacker Large Language Model

    CUHK-Shenzhen & SLAI

  18. Discovering Persistent Behavioural Patterns for Interpretable Blockchain Forensics

    Aug 13, 2026Dorottya Zelenyanszki, Zhe Hou, Kamanashis Biswas +1BlockchainMalicious Agents

    Griffith University, 170 Kessels Road, Nathan, 4111, QLD, Australia · Australian Catholic University, 1100 Nudgee Road, Banyo, 4014, QLD, Australia

  19. Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents

    Aug 13, 2026Xutao Mao, Liangjie Zhao, Xiang Zheng +1Large Language Model AgentsMalicious Agents

    1City University of Hong Kong · 2Adelaide University

  20. ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners

    Aug 10, 2026Puyu Zeng, Simeng Qin, Jingzhi Li +3Malicious AgentsMulti-Llm Agents

    College of Cryptology and Cyber Science, Nankai University, China · Northeastern University, China · University of Science and Technology Beijing, China +2

  21. ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization

    Aug 10, 2026Hao Sui, Simeng Qin, Jie Liao +3Clean Label Backdoor AttackMalicious Agents

    Nanjing University of Aeronautics and Astronautics, China · Northeastern University, China · Chongqing University, China +1

  22. SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

    Aug 9, 2026Xinze Chen, Chi Zhang, Ping Ji +1Malicious AgentsTaxonomy-Driven Dataflow Model

    The Graduate Center, City University of New York · New York, NY, USA · Hunter College, City University of New York +2

  23. Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario

    Aug 8, 2026Satoshi MatsuokaRealistic Threat ModelLarge Language Model Agents

    RIKEN Center for Computational Science, Kobe, Japan

  24. Robust Context-Aware Detection of Malicious Instructions in Text

    Aug 5, 2026Buzhao Liu, Xinhang Ma, Yevgeniy VorobeychikAttacker Large Language ModelIndirect Prompt Injection

    Washington University in St. Louis

  25. IMMENSE: Inductive Multi-perspective User Classification in Social Networks

    Aug 5, 2026Francesco Benedetti, Antonio Pellicani, Gianvito Pio +1Social MediaUser Modeling

    Department of Computer Science, University of Bari, Via Orabona 4, Bari, 70125, Italy · Department of Computer Science, University of Pisa, Largo Bruno Pontecorvo 3, Pisa, 56127, Italy · Data Science Laboratory, National Interuniversity Consortium for Informatics (CINI), Via Volturno 58, Roma, 00185, Italy +1

  26. ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection

    Jul 30, 2026Girish G N, Ashutosh Sahoo, Ajay Bhat +4Decentralized FinanceFraud Detection

    Zeru Finance · The Ohio State University, USA

  27. 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

  28. 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

  29. False Prophets: On the Security of World Models in Agentic Systems

    Jul 25, 2026Erik Imgrund, Anna Wimbauer, Klim Kireev +1World ModelsSecurity

    BIFOLD & TU Berlin Berlin, Germany

  30. 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

  31. Integrity of peer-to-peer distributed LLM inference under malicious nodes

    Jul 21, 2026Mert Cihangiroglu, Antonino NoceraPeer-To-PeerLarge Language Model Reliability

    DCALab, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy

  32. 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

  33. How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in Practice

    Jul 18, 2026Mahzabin Tamanna, Elizabeth Lin, Sparsha Gowda +2Artificial Intelligence SystemsInterviews

    North Carolina State University, USA

  34. ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm

    Jul 11, 2026Kefan Song, Yanjun QiAgentic DeploymentsMalicious Agents

    University of Virginia, Charlottesville, VA, USA

  35. Detecting Ladder Logic Bombs in IEC 61131-3 PLC Programs using ESBMC-PLC+: A Formal Verification Approach with Trigger Synthesis

    Jul 9, 2026Pierre Dantas, Lucas Cordeiro, Waldir JuniorFormal VerificationLadder

    Electrical Engineering Federal University of Amazonas (UFAM) Manaus, AM, Brazil

  36. When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

    Jul 7, 2026Haowen Xu, Xue Tan, Lei Ma +6Malicious AgentsLarge Language Model Backbones

    Department of Computer Science, Worcester Polytechnic Institute, MA, USA · School of Computer Science, Fudan University, Shanghai, China · Institute of Big Data, Fudan University, Shanghai, China +1

  37. CONTRA: Red-Teaming Configurations of Personalizable Agents

    Jul 3, 2026Jonathan Nöther, Adish Singla, Goran RadanovicRed-TeamingMalicious Agents

    Max Planck Institute for Software Systems, Germany

  38. Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring

    Jul 2, 2026William Hackett, Peter GarraghanGuardrailLarge Language Model Safety

    Mindgard · Lancaster University

  39. It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents

    Jun 26, 2026Yiming Sun, Chen Chen, Zifan Zhou +1Computer-Use AgentsArtificial Intelligence Agents

    Fudan University, JADE (Whitzard AI) Team

  40. Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries

    Jun 25, 2026Prarabdh Shukla, Ritik, Suhas Rao +2Jailbreak AttacksMalicious Agents

    Centre for Machine Intelligence and Data Science, IIT Bombay · Department of Computer Science and Engineering, IIT Bombay

  41. Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment

    Jun 24, 2026Aditya Singh, Gerson Kroiz, Senthooran Rajamanoharan +1Agent Behavior ModelingDigital Forensics

    MATS · Google DeepMind

  42. Detecting Malicious Agent Skills in the Wild using Attention

    Jun 22, 2026Bacem Etteib, Daniele Lunghi, Tégawendé F. BissyandéMalicious AgentsSkills

    University of Luxembourg

  43. When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents

    Jun 22, 2026Yanhang Li, Zhichao Fan, Zexin ZhuangIndirect Prompt InjectionMultimodal Evaluation

    Northeastern University Boston, Massachusetts, USA · University of Illinois Urbana-Champaign Urbana, Illinois, USA · Southern Methodist University Dallas, Texas, USA

  44. SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors

    Jun 21, 2026Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab +2Clean Label Backdoor AttackFederated Learning

    Department of Computer and Software Engineering, Polytechnique Montréal, Montreal, Quebec, Canada · Department of Computer Science, Khalifa University, Abu Dhabi, UAE

  45. Multi-View Decompilation for LLM-Based Malware Classification

    Jun 18, 2026Bercan Turkmen, Vyas RainaDisassemblyMalware

    Independent Researcher · SPARK

  46. FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection

    Jun 15, 2026Y. H. Zhou, Z. M. Ma, Y. J. Zhou +12Fraud DetectionBrowser Agent

  47. When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

    Jun 12, 2026Yihan Xia, Taotao WangReputationAI Trustworthiness

    Shenzhen University, China

  48. Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

    Jun 10, 2026Yitong Zhang, Shiteng Lu, Jia LiLarge Language Model JailbreaksJailbreak Attacks

    College of AI Tsinghua University Beijing, China · Yingcai Honors College University of Electronic Science and Technology of China Chengdu, China

  49. Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security

    Jun 10, 2026Tu Lan, Chaowei XiaoAgent Skill RetrievalMalicious Agents

    Johns Hopkins University

  50. POISE: Position-Aware Undetectable Skill Injection on LLM Agents

    Jun 6, 2026Haochang Hao, Dehai Min, Zhifang Zhang +4PoisoningMalicious Agents

    University of Illinois at Chicago · University of Queensland · 3Tulane University +1

  51. Adversarial Creation and Detection of AI-Generated Social Bot Content

    Jun 5, 2026Mykola Trokhymovych, Ricardo Baeza-Yates, Alessandro Flammini +2Ai-Generated Content DetectionGenerative Artificial Intelligence

    Universitat Pompeu Fabra, Barcelona, Spain · Observatory on Social Media, Indiana University, Bloomington, Indiana, USA · KTH Royal Institute of Technology, Stockholm, Sweden

  52. TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

    Jun 5, 2026Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli +7TracesTrajectory-Level Credit

    University of Massachusetts at Amherst · Adobe Research · Dolby Labs +2

  53. Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

    Jun 4, 2026Jingheng Ye, Huiqi Zou, Simon Yu +1SabotageCoding Agents

    Northeastern University1

  54. Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessment

    Jun 1, 2026Yiran Qiao, Jing Chen, Jiaqi Xu +3Out-Of-DistributionStreaming Video

    Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · ByteDance China, Hangzhou, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences +1

  55. SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

    Jun 1, 2026Yuting Ning, Zhehao Zhang, Yash Kumar Lal +8Malicious AgentsAgentic Workflows

    The Ohio State University · Amazon AGI · Stanford University

  56. Investigating and Alleviating Harm Amplification in LLM Interactions

    Jun 1, 2026Ruohao Guo, Wei Xu, Alan RitterLarge Language Model SafetyHarms

    Georgia Institute of Technology

  57. ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

    May 31, 2026Vincent Koc, Patrick Erichsen, Jacob Tomlinson +3Malicious AgentsMalware

    OpenClaw Foundation USA · NVIDIA United Kingdom · NVIDIA USA

  58. Inference Cost Attacks for Retrieval-Augmented Large Language Models

    May 31, 2026Chengliang Liu, Liangbo Ning, Yujuan Ding +1Agentic Retrieval-Augmented Generation SystemsAttacker Large Language Model

    The Hong Kong Polytechnic University Hong Kong, Hong Kong

  59. Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems

    May 30, 2026Ismail Hossain, Sai Puppala, Zhuoran Lu +2Malicious AgentsReusable Agent Skills

    University of Texas at El Paso, TX, USA · Southern Illinois University-Carbondale, IL, USA · Purdue University, IN, USA

  60. Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

    May 30, 2026Mohammed Sameer Syed, Rozhin YasaeiMalicious AgentsAI Trustworthiness

    University of Arizona