{"total":100,"rows":[{"id":"2503.22738","title":"ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning","created":"2025-03-26","cited_by_count":151,"area":"lr"},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136,"area":"lr"},{"id":"2406.09187","title":"GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning","created":"2024-06-13","cited_by_count":124,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92,"area":"lr"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"area":"lr"},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31,"area":"lr"},{"id":"2502.18695","title":"Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models","created":"2025-02-25","cited_by_count":31,"area":"lr"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"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":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2505.15404","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","created":"2025-05-21","cited_by_count":18,"area":"lr"},{"id":"2507.13255","title":"Automating Steering for Safe Multimodal Large Language Models","created":"2025-07-17","cited_by_count":17,"area":"lr"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"area":"lr"},{"id":"2404.03820","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","created":"2024-04-04","cited_by_count":15,"area":"lr"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2504.17130","title":"Steering the CensorShip: Uncovering Representation Vectors for LLM \"Thought\" Control","created":"2025-04-23","cited_by_count":14,"area":"lr"},{"id":"2501.17749","title":"Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation","created":"2025-01-29","cited_by_count":13,"area":"lr"},{"id":"2505.19684","title":"VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models","created":"2025-05-26","cited_by_count":13,"area":"lr"},{"id":"2510.00938","title":"Large Reasoning Models Learn Better Alignment from Flawed Thinking","created":"2025-10-01","cited_by_count":13,"area":"lr"},{"id":"2605.15239","title":"Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2512.21871","title":"Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?","created":"2025-12-26","cited_by_count":10,"area":"lr"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2505.17244","title":"ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models","created":"2025-05-22","cited_by_count":9,"area":"lr"},{"id":"2410.21791","title":"Enhancing Adversarial Attacks through Chain of Thought","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2512.02306","title":"OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning","created":"2025-12-02","cited_by_count":7,"area":"lr"},{"id":"2601.21051","title":"Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report","created":"2026-01-28","cited_by_count":7,"area":"lr"},{"id":"2505.16446","title":"Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2510.11570","title":"Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2605.17329","title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","created":"2026-05-17","cited_by_count":5,"area":"lr"},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2508.20151","title":"IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2510.17687","title":"CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks","created":"2025-10-20","cited_by_count":4,"area":"lr"},{"id":"2511.15169","title":"SafeRBench: Dissecting the Reasoning Safety of Large Language Models","created":"2025-11-19","cited_by_count":4,"area":"lr"},{"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":"2602.01600","title":"Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2508.19980","title":"Evaluating Language Model Reasoning about Confidential Information","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2509.23441","title":"Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.21049","title":"Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2601.03662","title":"How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2602.18193","title":"BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2606.01991","title":"SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2606.04425","title":"What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection","created":"2026-06-03","cited_by_count":3,"area":"lr"},{"id":"2509.22250","title":"Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2510.08592","title":"Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models","created":"2025-10-04","cited_by_count":2,"area":"lr"},{"id":"2510.15007","title":"Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2510.17057","title":"The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2511.12113","title":"MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge through Group Direct Preference Optimization","created":"2025-11-15","cited_by_count":2,"area":"lr"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2603.25412","title":"Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2508.10390","title":"Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts","created":"2025-08-14","cited_by_count":1,"area":"lr"},{"id":"2509.19775","title":"bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2511.06160","title":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2603.15417","title":"Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities","created":"2026-03-16","cited_by_count":1,"area":"lr"},{"id":"2604.09750","title":"Conflicts Make Large Reasoning Models Vulnerable to Attacks","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"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":"2605.08936","title":"Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2605.17113","title":"The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning","created":"2026-05-16","cited_by_count":1,"area":"lr"},{"id":"2605.29068","title":"Robust and Efficient Guardrails with Latent Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.08234","title":"SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2606.26686","title":"Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2607.17575","title":"A Dual-Hypothesis Reasoning Framework for LLM Guardrails","created":"2026-07-20","cited_by_count":1,"area":"lr"},{"id":"2607.21401","title":"When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2509.05367","title":"Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs","created":"2025-09-04","cited_by_count":0,"area":"lr"},{"id":"2602.06650","title":"Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2603.10091","title":"Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2604.10502","title":"CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.10504","title":"CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2605.12746","title":"CoT-Guard: Small Models for Strong Monitoring","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2607.06326","title":"DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2608.03838","title":"LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.09542","title":"Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.15594","title":"TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.22915","title":"Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2608.24232","title":"TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2609.34896","title":"DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.16312","title":"Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18304","title":"Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.18566","title":"Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}