{"total":67,"rows":[{"id":"2602.20867","title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","created":"2026-02-24","cited_by_count":130,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37,"area":"agents"},{"id":"2505.10924","title":"A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?","created":"2025-05-16","cited_by_count":23,"area":"agents"},{"id":"2601.05293","title":"A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2601.01592","title":"OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs","created":"2026-01-04","cited_by_count":21,"area":"mllm"},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2508.03125","title":"Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS","created":"2025-08-05","cited_by_count":17,"area":"agents"},{"id":"2605.25002","title":"MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems","created":"2026-05-24","cited_by_count":16,"area":"agents"},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2505.18812","title":"SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models","created":"2025-05-24","cited_by_count":8,"area":"mllm"},{"id":"2602.11749","title":"AIR: Improving Agent Safety through Incident Response","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2607.01793","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2607.01236","title":"Safeguarding LLM Agents from Misalignment through Provenance Analysis","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2511.18921","title":"BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models","created":"2025-11-24","cited_by_count":5,"area":"mllm"},{"id":"2603.15408","title":"TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2507.12314","title":"Thought Purity: A Defense Framework For Chain-of-Thought Attack","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2601.17003","title":"Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2601.21233","title":"Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs","created":"2026-01-29","cited_by_count":4,"area":"agents"},{"id":"2602.01025","title":"Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models","created":"2026-02-01","cited_by_count":4,"area":"mllm"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2510.22242","title":"PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2602.14281","title":"MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2604.01346","title":"Safety, Security, and Cognitive Risks in World Models","created":"2026-04-01","cited_by_count":3,"area":"wm"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2605.25389","title":"Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS","created":"2026-05-25","cited_by_count":3,"area":"agents"},{"id":"2608.05695","title":"DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model","created":"2026-08-06","cited_by_count":3,"area":"wm"},{"id":"2601.22737","title":"Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models","created":"2026-01-30","cited_by_count":2,"area":"mllm"},{"id":"2604.15579","title":"Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents","created":"2026-04-16","cited_by_count":2,"area":"safety"},{"id":"2606.27027","title":"ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP","created":"2026-06-25","cited_by_count":2,"area":"agents"},{"id":"2506.19079","title":"Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition","created":"2025-06-23","cited_by_count":1,"area":"mllm"},{"id":"2507.00026","title":"RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2511.17362","title":"ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2601.19507","title":"Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2602.06623","title":"Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2603.08234","title":"The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs","created":"2026-03-09","cited_by_count":1,"area":"safety"},{"id":"2603.13359","title":"From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions","created":"2026-03-09","cited_by_count":1,"area":"alignment"},{"id":"2605.01899","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2605.06731","title":"When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.20874","title":"Governance by Construction for Generalist Agents","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2606.03089","title":"Constitutional On-Policy Safe Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2603.03536","title":"SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2603.09706","title":"OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences","created":"2026-03-10","cited_by_count":0,"area":"mllm"},{"id":"2603.12799","title":"What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models","created":"2026-03-13","cited_by_count":0,"area":"mllm"},{"id":"2604.05809","title":"Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2605.00443","title":"Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.17577","title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","created":"2026-05-17","cited_by_count":0,"area":"mllm"},{"id":"2605.18868","title":"DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.13078","title":"Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.00543","title":"Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor","created":"2026-08-01","cited_by_count":0,"area":"diffusion"},{"id":"2608.00677","title":"OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution","created":"2026-08-01","cited_by_count":0,"area":"safety"},{"id":"2608.09577","title":"ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.10530","title":"On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2609.06835","title":"Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.20080","title":"A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed Forces","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.33833","title":"One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35028","title":"VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01944","title":"Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14701","title":"Towards Merging-conditional Backdoor Unalignment against Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"},{"id":"2610.17613","title":"MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}