{"total":62,"rows":[{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"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":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"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":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2510.27062","title":"Consistency Training Helps Stop Sycophancy and Jailbreaks","created":"2025-10-31","cited_by_count":16,"area":"safety"},{"id":"2410.03857","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","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":"2509.21947","title":"Active Attacks: Red-teaming LLMs via Adaptive Environments","created":"2025-09-26","cited_by_count":7,"area":"safety"},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6,"area":"safety"},{"id":"2511.04316","title":"AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research","created":"2025-11-06","cited_by_count":6,"area":"safety"},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2503.11185","title":"Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks","created":"2025-03-14","cited_by_count":5,"area":"safety"},{"id":"2505.21347","title":"OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models","created":"2025-05-27","cited_by_count":5,"area":"safety"},{"id":"2510.04891","title":"SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests","created":"2025-10-06","cited_by_count":5,"area":"safety"},{"id":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2504.09604","title":"Mitigating Many-Shot Jailbreaking","created":"2025-04-13","cited_by_count":4,"area":"safety"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"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":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","cited_by_count":3,"area":"safety"},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2502.14975","title":"Beyond No: Quantifying AI Over-Refusal and Emotional Attachment Boundaries","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2603.02588","title":"ExpGuard: LLM Content Moderation in Specialized Domains","created":"2026-03-03","cited_by_count":2,"area":"safety"},{"id":"2607.13075","title":"The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators","created":"2026-07-12","cited_by_count":2,"area":"safety"},{"id":"2607.19806","title":"OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization","created":"2026-07-22","cited_by_count":2,"area":"safety"},{"id":"2503.03502","title":"Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension","created":"2025-03-05","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":"2509.25843","title":"ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2605.08496","title":"Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms","created":"2026-05-08","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":"2606.16527","title":"DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing","created":"2026-06-15","cited_by_count":1,"area":"safety"},{"id":"2606.29887","title":"SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing","created":"2026-06-29","cited_by_count":1,"area":"safety"},{"id":"2609.16204","title":"Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration","created":"2026-09-14","cited_by_count":1,"area":"safety"},{"id":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"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":"2605.24535","title":"Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2605.24552","title":"Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling","created":"2026-05-23","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":"2606.26377","title":"Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2606.31748","title":"Addressing Over-Refusal in LLMs with Competing Rewards","created":"2026-06-30","cited_by_count":0,"area":"safety"},{"id":"2607.20472","title":"Robust Critics: Defending LLMs Against Multi-Turn Attacks","created":"2026-05-24","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":"2607.24392","title":"When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs","created":"2026-07-27","cited_by_count":0,"area":"safety"},{"id":"2609.00790","title":"RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.01046","title":"HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation","created":"2026-09-01","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":"2609.05797","title":"Safety Monitors Mostly Catch What the Model Already Refuses","created":"2026-09-05","cited_by_count":0,"area":"safety"},{"id":"2609.06540","title":"SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure","created":"2026-09-06","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":"2609.21484","title":"HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.32602","title":"AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion","created":"2026-09-26","cited_by_count":0,"area":"safety"},{"id":"2609.33671","title":"COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints","created":"2026-09-27","cited_by_count":0,"area":"safety"},{"id":"2609.36657","title":"Constitutional adapters: Inference-time interventions for misalignment and misuse","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2610.01497","title":"OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.15218","title":"Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models","created":"2026-10-10","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}