Benign

Ask about this topic

Momentum

1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 28

All topics
CardsList

  1. Safety of Latent Communication in Multi-Agent Systems

    Sep 30, 2026Muhammad Huzaifa, Sina Mavali, Thorsten EisenhoferSafety AlignmentBenign

    CISPA Helmholtz Center for Information Security, Saarbrücken, Germany

  2. When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

    Sep 1, 2026Yitong Guo, Xiaoyi Chen, Siyuan Zhang +2FragilityModel Fine-Tuning

    Indiana University Bloomington · Tsinghua University · Nanyang Technological University

  3. Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text

    Aug 31, 2026Minkyung Cho, Jihyo Kim, SeungWoo Song +4Synthetic DataBenign

    KAIST · KAIST InnoCORE PRISM-AI Center · Department of Artificial Intelligence, Dankook University

  4. Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation

    Aug 12, 2026Haoyu Zhang, Haowen Xu, Xiao Luo +7Large Language Model SafetyBenign

    Northeastern University

  5. Benign interpolation and Occam's razor

    Aug 4, 2026Tom F. Sterkenburg, Daniel A. Herrmann, Jan-Willem RomeijnStochastic InterpolantsInterpretability

  6. Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity

    Aug 4, 2026Chinmoy Mitra, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood +2Federated LearningBalanced Learning

    Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Kazla, Rajshahi, 6204, Bangladesh · Department of Electrical and Computer Engineering, North South University, Dhaka 1229, Bangladesh. · Department of Computer Science, Missouri State University, Springfield, MO, 65809, USA. +2

  7. When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

    Jul 13, 2026Yibo Hu, Ren WangBenignTraces

    Illinois Institute of Technology

  8. Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

    Jul 7, 2026Qi Zhao, Christian WressneggerPoisoningBenign

    KASTEL Security Research Labs · Karlsruhe Institute of Technology (KIT)

  9. 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

  10. PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement

    Jul 3, 2026Xianren Zhang, Delvin Ce Zhang, Dongwon Lee +1Large Language Model UnlearningMultimodal Large Language Models

    The Pennsylvania State University · University of Sheffield

  11. Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine

    Jul 1, 2026Jiaxian Lv, Shiyao Cui, Yingkang Wang +3Content ModerationToxicity

    The Conversational AI (CoAI) Group, DCST, Tsinghua University

  12. Defending Against Harmful Supervision Hidden in Benign Samples

    Jun 29, 2026Bang An, Yibo Yang, Dandan Guo +3Supervised FinetuningModel-Agnostic Defense

    1King Abdullah University of Science and Technology · School of Artificial Intelligence, Jilin University

  13. The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

    Jun 27, 2026Will Hawkins, Kaivalya Rawal, Jonathan Rystrøm +8Multilingual SafetyLarge Language Model Safety

    Oxford Internet Institute, University of Oxford · Hasso Plattner Institute, University of Potsdam · Chinese University of Hong Kong +2

  14. Misinformation Propagation in Benign Multi-Agent Systems

    Jun 15, 2026Jonas Becker, Jan Philip Wahle, Terry Ruas +1Multi-Agent DebateMisinformation

    University of Göttingen, Germany · LKA NRW, Germany

  15. MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents

    Jun 9, 2026Pratibha Revankar, Kargi Chauhan, Jihye Kim +3Attacker Large Language ModelLarge Language Model Agents

    University of California, Santa Cruz.

  16. DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

    May 29, 2026Junbo Zhang, Qianli Zhou, Xinyang Deng +3Large Language Model SafetyLarge Language Model Fine-Tuning

  17. SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents

    May 27, 2026Yubin Qu, Yi Liu, Gelei Deng +4Coding AgentsSynthetic Environments

    1Griffith University · 2Quantstamp · 3Nanyang Technological University +2

  18. Safety-Oriented Routing Analysis of Mixtral MoE Under Benign and Harmful Prompts

    May 22, 2026Md Nurul Absar SiddikyMixture-Of-Experts Large Language ModelsLarge Language Model Routing

    Department of Electrical and Computer Engineering University of Hawai’i at M¯anoa Honolulu, HI, USA

  19. Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

    May 18, 2026John T. Halloran, Noopur S. BhattAttacker Large Language ModelPoisoning

    Leidos · University of Pennsylvania

  20. Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection

    May 18, 2026Juozas Dautartas, Olga Kurasova, Juozapas Rokas Čypas +1MalwareEvasion

    Institute of Data Science and Digital Technologies, Faculty of Mathematics and Informatics, Vilnius University, LT-08412 Vilnius, Lithuania

  21. Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks

    May 18, 2026Yubin Qu, Ying Zhang, Yanjun Zhang +4Kernel-Resident Tool Governance GatewayCoding Agents

    Griffith University · Wake Forest University · Nanyang Technological University +2

  22. FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments

    May 10, 2026Astha Mehta, Niruthiha Selvanayagam, Cedric Lam +10Large Language Model SafetyBenign

    Isabella · ÉTS Montreal / SPAR · Mila / Lida Safety

  23. Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs

    May 9, 2026Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2BenignRefusals

    Yonsei University

  24. GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training

    May 8, 2026Henghui Xu, Yuchen Zhang, Xiaobo MaGeneralist Graph Anomaly DetectionIntrusion Detection

    MOE Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China · Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, China · Shaanxi Province Key Laboratory of Computer Network, Xi’an Jiaotong2026 University, Xi’an, China

  25. How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning

    Apr 21, 2026Haoyang Chen, Yi Liu, Jianzhi Shao +3Reasoning TracesLinear Activation Steering

    State Key Laboratory for Novel Software Technology, Nanjing University, China · Alibaba Group, China · Ant Group, China

  26. Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

    Apr 17, 2026Jaechul Roh, Virat Shejwalkar, Amir HoumansadrLarge Audio Language ModelsModel Fine-Tuning

    University of Massachusetts Amherst

  27. Seven Security Challenges in Cross-domain Multi-agent LLM Systems

    May 28, 2025Ronny Ko, Jiseong Jeong, Shuyuan Zheng +4Multi-Agent Large Language Model SystemsLarge Language Model Safety

    Osaka University · Seoul National University · Yonsei University

  28. Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning

    May 22, 2025Thibaud Gloaguen, Mark Vero, Robin Staab +1Large Language Model Fine-TuningModel Fine-Tuning

    ETH Zurich