Adversaries

Follow this topic Ask about this topic

Recent momentum

-46%

13 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

8 new papers

A weekly snapshot of new work published in Adversaries.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Adversaries.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Adversaries.

184 papers

Latest in Adversaries

Browse all topics →

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
May 12, 2026Chang Jin, An Wang, Zeming Wei +7Safety Large Language Model Agents
Adaptive Calibration in Non-Stationary Environments
May 12, 2026Junyan Liu, Haipeng Luo, Lillian J. RatliffNon-Stationarity Adversaries
Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
May 12, 2026Shoumik Saha, Kazem Faghih, Soheil FeiziReusable Agent Skills Agent Skill Ecosystems
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
May 11, 2026Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu +2Federated Learning Backdoor Attacks
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
May 11, 2026Hongwei Yao, Yiming Liu, Yiling He +1Openclaw Security Analysis
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
May 11, 2026Peiru Yang, Haoran Zheng, Tong Ju +6Multi-Source Retrieval-Augmented Generation Multimodal Clinical Data
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
May 9, 2026Xinyu Li, Ronghui Mu, Lin Li +2Language Model Evasion Attacks Large Language Model Reasoning
Tight Generalization Bounds for Noiseless Inverse Optimization
May 9, 2026Pouria Fatemi, Hoomaan Maskan, Suvrit Sra +1Stochastic Optimization Generalization Bounds
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
May 8, 2026Lennart Wachowiak, Scott D. Blain, David Williams-King +1Language Model Evasion Attacks Large Language Model Decision-Making
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
May 8, 2026Hanzaleh Akbari Nodehi, Parsa Moradi, Soheil Mohajer +1Learning-Augmented Algorithms Adversarial Training
Multi-Armed Bandits With Best-Action Queries
May 8, 2026Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi +1Multi-Armed Bandits O(T^Β)$ Simultaneous Regret
Repeated Deceptive Path Planning against Learnable Observer
May 8, 2026Shiyue Cao, Pei Xu, Likun Yang +6Coverage Path Planning Reinforcement-Learning Policies
Insider Attacks in Multi-Agent LLM Consensus Systems
May 8, 2026Xiaolin Sun, Zixuan Liu, Yibin Hu +1Multi-Agent Large Language Model Adversaries
Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
May 7, 2026Guanmeng Xian, Ning Yang, Philip S. YuAdversarial Transferability Adversarial Training
Constrained Contextual Bandits with Adversarial Contexts
May 7, 2026Dhruv Sarkar, Abhishek SinhaLinear Contextual Bandits Optimal Bandit Algorithms
Adversarial Effects on Expressibility and Trainability in Distributed Variational Quantum Algorithms
May 5, 2026Abhishek Sadhu, Sharu Theresa JoseVariational Quantum Circuits Quantum Machine Learning
Distributed Learning with Adversarial Gradient Perturbations
May 5, 2026Nawapon Sangsiri, Yufei TaoDistributional Learning Optimal Sample Complexity
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
May 4, 2026Ruofeng Yang, Yongcan Li, Shuai LiAutoresearch Adversarial Evaluation
When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning
May 4, 2026Arahan KujurSelf-Play Adversaries
Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
May 3, 2026Youngmin OhBandits Delay
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
May 1, 2026Sheldon Yu, Yingcheng Sun, Hanqing Guo +1Language Model Evasion Attacks Llm-Based Agent
Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders
Apr 30, 2026Emma Andrews, Sahan Sanjaya, Prabhat MishraQuantum Machine Learning Adversarial Examples
Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
Apr 30, 2026Prashant KulkarniAdversarial Examples Indirect Prompt Injection
What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design
Apr 30, 2026Ivan BercovichAgentic Benchmarks Adversarial Evaluation
AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation
Apr 29, 2026Xu Wang, Zexian Li, Litong Gong +2Few-Step Generation Ad
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Apr 29, 2026Hanna Foerster, Ilia Shumailov, Cheng Zhang +3Extreme Low-Bit Quantization Quantizer
The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
Apr 29, 2026Vishesh Kumar, Akshay AgarwalAdversarial Examples Adversarial Transferability
Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM
Apr 28, 2026Vinith M. Suriyakumar, Ayush Sekhari, Lena Stempfle +5Large Language Model Evaluation Adversaries
Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models
Apr 25, 2026Max Hartman, Vidhata Jayaraman, Moulik Choraria +2Asymmetric Distillation Reasoning Traces
From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks
Apr 25, 2026Nilanjana Das, Mathew Dawit, Aman Chadha +1Jailbreaks Vulnerable Code
CSC: Turning the Adversary's Poison against Itself
Apr 23, 2026Yuchen Shi, Xin Guo, Huajie Chen +3Backdoor Attacks Model-Agnostic Defense
Supervised Learning Has a Necessary Geometric Blind Spot: Theory, Consequences, and Minimal Repair
Apr 23, 2026Vishal RajputSupervised Learning Adversaries
Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation
Apr 22, 2026Jiahao Xu, Xiaohan Yuan, Xingchen Wu +3Articulated Objects Human Motion Generation
Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery
Apr 21, 2026Abhinav AgarwalVulnerability Detection & Repair Defect
How Adversarial Environments Mislead Agentic AI?
Apr 20, 2026Zhonghao Zhan, Huichi Zhou, Zhenhao Li +3Adversaries Multiple Attack Surfaces
Scalable Neighborhood-Based Multi-Agent Actor-Critic
Apr 20, 2026Tim Goppelsroeder, Rasmus JensenMulti-Agent Reinforcement Learning Critic-Free Reinforcement Learning
Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition
Apr 20, 2026Prasoon Goyal, Sattvik Sahai, Michael Johnston +14Large Language Model Generation Conversational Datasets
Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
Apr 20, 2026Seunghee Koh, Sunghyun Baek, Youngdong Kim +1Token-Level Uncertainty Adversaries
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
Apr 18, 2026Jiayuan Liu, Shiyi Du, Weihua Du +2Multi-Agent Large Language Model Collaboration
SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
Apr 17, 2026Hikaru Shindo, Hanzhao Lin, Lukas Helff +2Social Reasoning Multi-Agent Systems
The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment
Apr 16, 2026Songlin Li, Zhiqing Guo, Dan Ma +2Photometric Supervision Adjudication
Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
Apr 3, 2026Solon Falas, Markos Asprou, Charalambos Konstantinou +1Conventional Physics-Informed Neural Networks State Estimation
Walma: Learning to See Memory Corruption in WebAssembly
Mar 25, 2026Oussama Draissi, Mark Günzel, Ahmad-Reza Sadeghi +1Canonical Action Verification And Attestation Vulnerability Detection & Repair
Bayesian Adversarial Privacy
Mar 4, 2026Cameron Bell, Timothy Johnston, Antoine Luciano +1Efficient Privacy Loss Differential Privacy
Generating adversarial inputs for a graph neural network model of AC power flow
Feb 20, 2026Robert ParkerAc Optimal Power Flow Neural Network Verification
From Legible to Inscrutable Trajectories: (Il)legible Motion Planning Accounting for Multiple Observers
Feb 9, 2026Ananya Yammanuru, Maria Lusardi, Nancy M. Amato +1Motion Planners Trajectory Prediction
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
Feb 9, 2026Yuting Ning, Jaylen Jones, Zhehao Zhang +5Computer-Use Agents Artificial Intelligence Detection
Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
Feb 2, 2026Mingyi Li, Taira Tsuchiya, Kenji YamanishiNear-Optimal Regret Guarantees Markov Decision Processes
Policy Stability for Measuring Operational Performance in Task Assignment with Time-Windows Under Internal Adversarial Influence
Nov 7, 2025Roee M. Francos, Daniel Garces, Orhan Eren Akgün +1Vehicle Routing Problem Stochastic Delays
Rethinking Robust Adversarial Concept Erasure in Diffusion Models
Oct 31, 2025Qinghong Yin, Yu Tian, Heming Yang +5Concept Erasure Adversarial Transferability
Adaptive Conformal Inference through the Lens of Blackwell Approachability
Oct 17, 2025Guillaume Principato, Gilles StoltzConformal Inference Bayesian
LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition
Oct 10, 2025Yushuo Zheng, Tongrui Ye, Zicheng Zhang +3Evaluation Benchmarks Artificial Intelligence Evaluation
Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints
Sep 24, 2025Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni +2Markov Decision Processes O(T^Β)$ Simultaneous Regret
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered Scenes
Aug 23, 2025Haozhuo Zhang, Jingkai Sun, Michele Caprio +5Long-Tail Humanoid Whole-Body Control Human Motion
Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
Aug 9, 2025Jinhwa Kim, Ian G. HarrisAdversarial Jailbreaks Model-Agnostic Defense
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Jun 25, 2025Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5Red-Teaming Code Generation
Variational Learning of Disentangled Representations
Jun 20, 2025Yuli Slavutsky, Ozgur Beker, David Blei +1Variational Covariate Shift
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
May 22, 2025Thibaud Gloaguen, Mark Vero, Robin Staab +1Language Model Evasion Attacks Large Language Model Fine-Tuning
Attention is All You Need Until You Need Retention
Jan 15, 2025M. Murat YasliogluRetention Generative Pretrained Transformers
DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment
Aug 23, 2024Yoshitaka Inoue, Tianci Song, Xinling Wang +3Drug-Drug Interactions Systematic Review

May 12, 2026 · cs.CRJ/K move · Enter open · S save

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

Chang Jin, An Wang, Zeming Wei, Kai Wang+6

1Shanghai AI Laboratory · 2Peking University · 3East China Normal University

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: even when the user request is benign, unsafe influence may reside in skill guidance, local artifacts, or execution-environment files that steer the agent toward unsafe actions. We present SkillSafetyBench, a runnable benchmark for evaluating such skill-mediated safety failures. SkillSafetyBench includes 155 adversarial cases across 47 tasks, 6 risk domains, and 30 safety categories, each evaluated with a case-specific rule-based verifier. Experiments with multiple CLI agents and model backends show that non-user attacks can consistently induce unsafe behavior, with distinct failure patterns across domains, attack methods, and scaffold-model pairings. Our findings suggest that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.

Safety Large Language Model Agents Adversaries

Open paper Ask about it PDF