{"total":74,"rows":[{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151,"area":"lr"},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91,"area":"lr"},{"id":"2502.11448","title":"AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection","created":"2025-02-17","cited_by_count":89,"area":"agents"},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2503.15754","title":"AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration","created":"2025-03-20","cited_by_count":43,"area":"safety"},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2504.14064","title":"DoomArena: A framework for Testing AI Agents Against Evolving Security Threats","created":"2025-04-18","cited_by_count":32,"area":"agents"},{"id":"2503.09347","title":"Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts","created":"2025-03-12","cited_by_count":26,"area":null},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2503.01865","title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints","created":"2025-02-25","cited_by_count":11,"area":"safety"},{"id":"2511.16842","title":"Fantastic Bugs and Where to Find Them in AI Benchmarks","created":"2025-11-20","cited_by_count":11,"area":null},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2510.02833","title":"Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs","created":"2025-10-03","cited_by_count":10,"area":"alignment"},{"id":"2505.20824","title":"MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems","created":"2025-05-27","cited_by_count":9,"area":"agents"},{"id":"2511.12710","title":"Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs","created":"2025-11-16","cited_by_count":8,"area":"safety"},{"id":"2501.09749","title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2508.05464","title":"Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?","created":"2025-08-07","cited_by_count":6,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2509.03487","title":"SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models","created":"2025-09-03","cited_by_count":5,"area":"safety"},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","cited_by_count":5,"area":"safety"},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2501.15693","title":"Beyond Benchmarks: On The False Promise of AI Regulation","created":"2025-01-26","cited_by_count":4,"area":null},{"id":"2511.20994","title":"GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2503.11572","title":"Implicit Bias-Like Patterns in Reasoning Models","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2506.07402","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","created":"2025-06-09","cited_by_count":3,"area":"alignment"},{"id":"2506.23725","title":"PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?","created":"2025-06-30","cited_by_count":3,"area":"mllm"},{"id":"2509.10104","title":"AI Harmonics: a human-centric and harms severity-adaptive AI risk assessment framework","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2510.15499","title":"HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2510.21460","title":"Risk Management for Mitigating Benchmark Failure Modes: BenchRisk","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2606.01481","title":"SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation","created":"2026-05-31","cited_by_count":3,"area":"diffusion"},{"id":"2502.07771","title":"Breaking Down Bias: On The Limits of Generalizable Pruning Strategies","created":"2025-02-11","cited_by_count":2,"area":null},{"id":"2505.14215","title":"Safety Degradation in AI Agents","created":"2025-05-20","cited_by_count":2,"area":"agents"},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2511.21758","title":"A Longitudinal Measurement of Privacy Policy Evolution for Large Language Models","created":"2025-11-24","cited_by_count":2,"area":"agents"},{"id":"2512.01848","title":"Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2606.00288","title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2508.15526","title":"SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking","created":"2025-08-21","cited_by_count":1,"area":"agents"},{"id":"2511.00029","title":"Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts","created":"2025-10-26","cited_by_count":1,"area":"mechinterp"},{"id":"2512.04843","title":"From Symptoms to Systems: An Expert-Guided Approach to Understanding Risks of Generative AI for Eating Disorders","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2602.11786","title":"Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2603.01630","title":"SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.13933","title":"OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset","created":"2026-03-14","cited_by_count":1,"area":"safety"},{"id":"2604.09606","title":"Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.19887","title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2608.17183","title":"Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2512.23747","title":"State-of-the-art Small Language Coder Model: Mify-Coder","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2604.18510","title":"Behind Harmful Compliance: Behavioral and Mechanistic Divergence Across LLM Jailbreaks","created":"2026-04-20","cited_by_count":0,"area":"safety"},{"id":"2605.00245","title":"ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.06213","title":"Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.14152","title":"ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2606.08376","title":"RiskNet: A large-scale dataset of AI risk incidents from news with alignment and multi-dimensional annotations","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.09178","title":"Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2606.20626","title":"Efficient Safety Benchmarking via Item Response Theory","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.22671","title":"AIR-BENCH Live: An Evolving Safety Benchmark for Foundation Models","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.13840","title":"ASSERT: A Measurement Pipeline for GenAI Audits","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.23870","title":"Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.26682","title":"From Alignment to Access Control: A Framework for GenAI Policy Enforcement","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33282","title":"Multi-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01535","title":"False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}