{"total":63,"rows":[{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69,"area":"safety"},{"id":"2410.09102","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy","created":"2024-10-09","cited_by_count":67,"area":"safety"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2412.05934","title":"Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models","created":"2024-12-08","cited_by_count":33,"area":"safety"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2506.17209","title":"Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency","created":"2025-06-20","cited_by_count":27,"area":"safety"},{"id":"2506.14922","title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","created":"2025-06-17","cited_by_count":24,"area":"safety"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2508.07646","title":"Multi-Turn Jailbreaks Are Simpler Than They Seem","created":"2025-08-11","cited_by_count":17,"area":"safety"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2601.18076","title":"Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming","created":"2026-01-26","cited_by_count":15,"area":"safety"},{"id":"2502.15086","title":"Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models","created":"2025-02-20","cited_by_count":10,"area":"safety"},{"id":"2510.17633","title":"SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering","created":"2025-10-20","cited_by_count":8,"area":"safety"},{"id":"2605.01687","title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","created":"2026-05-03","cited_by_count":8,"area":"safety"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2502.00735","title":"`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs","created":"2025-02-02","cited_by_count":7,"area":"safety"},{"id":"2510.10994","title":"Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety","created":"2025-10-13","cited_by_count":7,"area":"safety"},{"id":"2408.16163","title":"FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)","created":"2024-08-28","cited_by_count":6,"area":"safety"},{"id":"2501.03266","title":"LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena","created":"2025-01-04","cited_by_count":6,"area":"safety"},{"id":"2503.10192","title":"Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives","created":"2025-03-13","cited_by_count":6,"area":"safety"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2510.16629","title":"On the Impossibility of Retrain Equivalence in Machine Unlearning","created":"2025-10-18","cited_by_count":6,"area":"safety"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2508.04196","title":"Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models","created":"2025-08-06","cited_by_count":4,"area":"safety"},{"id":"2510.26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","created":"2025-10-30","cited_by_count":4,"area":"safety"},{"id":"2510.27087","title":"Characterizing Selective Refusal Bias in Large Language Models","created":"2025-10-31","cited_by_count":4,"area":"safety"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2605.00706","title":"FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios","created":"2026-05-01","cited_by_count":3,"area":"safety"},{"id":"2409.17458","title":"RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking","created":"2024-09-26","cited_by_count":2,"area":"safety"},{"id":"2412.12192","title":"No Free Lunch for Defending Against Prefilling Attack by In-Context Learning","created":"2024-12-13","cited_by_count":2,"area":"safety"},{"id":"2506.05376","title":"A Red Teaming Roadmap Towards System-Level Safety","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2506.21972","title":"Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses","created":"2025-06-27","cited_by_count":2,"area":"safety"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2510.10271","title":"MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation","created":"2025-10-11","cited_by_count":2,"area":"safety"},{"id":"2605.04700","title":"Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization","created":"2026-05-06","cited_by_count":2,"area":"safety"},{"id":"2606.08044","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","created":"2026-06-06","cited_by_count":2,"area":"safety"},{"id":"2410.05305","title":"Output Scouting: Auditing Large Language Models for Catastrophic Responses","created":"2024-10-04","cited_by_count":1,"area":"safety"},{"id":"2506.01770","title":"ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2506.16575","title":"Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System","created":"2025-06-19","cited_by_count":1,"area":"safety"},{"id":"2605.13334","title":"LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs","created":"2026-05-13","cited_by_count":1,"area":"safety"},{"id":"2606.04483","title":"Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenres","created":"2026-06-03","cited_by_count":1,"area":"safety"},{"id":"2606.11409","title":"Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models","created":"2026-06-09","cited_by_count":1,"area":"safety"},{"id":"2606.12342","title":"ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing","created":"2026-06-10","cited_by_count":1,"area":"safety"},{"id":"2608.14577","title":"HarmProfile: Characterizing Harmful Distributions in Frontier LLMs","created":"2026-06-11","cited_by_count":1,"area":"safety"},{"id":"2507.06282","title":"The bitter lesson of misuse detection","created":"2025-07-08","cited_by_count":0,"area":"safety"},{"id":"2508.13246","title":"Involuntary Jailbreak: On Self-Prompting Attacks","created":"2025-08-18","cited_by_count":0,"area":"safety"},{"id":"2605.29659","title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.23884","title":"One Year Later...The Harms Persist, But So Do We!","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2606.25750","title":"RAS: Measuring LLM Safety Through Refusal Alignment","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2606.25782","title":"Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2607.17152","title":"How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions","created":"2026-07-19","cited_by_count":0,"area":"safety"},{"id":"2607.22926","title":"SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI","created":"2026-07-24","cited_by_count":0,"area":"safety"},{"id":"2608.13304","title":"Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety","created":"2026-08-13","cited_by_count":0,"area":"safety"},{"id":"2609.05117","title":"TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors","created":"2026-09-04","cited_by_count":0,"area":"safety"},{"id":"2609.19630","title":"From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.35544","title":"Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.02827","title":"MLCommons Jailbreak Benchmark v1.0","created":"2026-10-02","cited_by_count":0,"area":"safety"},{"id":"2610.16761","title":"Separating Prompt Harmfulness from Interaction Safety via Partial Generation","created":"2026-10-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}