{"total":85,"rows":[{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244,"area":"lr"},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573,"area":"lr"},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"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":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2502.11054","title":"Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-02-16","cited_by_count":64,"area":"lr"},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"area":"lr"},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"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":"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":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"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":"2402.10601","title":"When \"Competency\" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers","created":"2024-02-16","cited_by_count":30,"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":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"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":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"id":"2503.01781","title":"Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models","created":"2025-03-03","cited_by_count":23,"area":"lr"},{"id":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2405.20902","title":"Preemptive Answer \"Attacks\" on Chain-of-Thought Reasoning","created":"2024-05-31","cited_by_count":19,"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":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","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":"2501.19180","title":"Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning","created":"2025-01-31","cited_by_count":11,"area":"lr"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"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":"2503.19134","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","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":"2407.16205","title":"Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models","created":"2024-07-23","cited_by_count":8,"area":"lr"},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"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":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","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":"2412.18770","title":"Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models","created":"2024-12-25","cited_by_count":6,"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":"2506.05038","title":"Toward Automated Robustness Evaluation of Mathematical Reasoning","created":"2025-06-05","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":"2512.05853","title":"VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2409.06241","title":"DiPT: Enhancing LLM reasoning through diversified perspective-taking","created":"2024-09-10","cited_by_count":4,"area":"lr"},{"id":"2504.01931","title":"On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows","created":"2025-04-02","cited_by_count":4,"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":"2508.04204","title":"ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments","created":"2025-08-06","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":"2603.15661","title":"DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2604.09748","title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","created":"2026-04-10","cited_by_count":3,"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":"2602.01795","title":"RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse","created":"2026-02-02","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":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2606.02041","title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2501.01872","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","created":"2025-01-03","cited_by_count":1,"area":"lr"},{"id":"2508.03054","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","created":"2025-08-05","cited_by_count":1,"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":"2510.17759","title":"VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2510.24446","title":"SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space","created":"2025-10-28","cited_by_count":1,"area":"lr"},{"id":"2511.08055","title":"MSCR: Exploring the Vulnerability of LLMs' Mathematical Reasoning Abilities Using Multi-Source Candidate Replacement","created":"2025-11-11","cited_by_count":1,"area":"lr"},{"id":"2601.03416","title":"GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2602.04224","title":"RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2604.09665","title":"Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model","created":"2026-04-01","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":"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":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2511.21214","title":"Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models","created":"2025-11-26","cited_by_count":0,"area":"lr"},{"id":"2603.02675","title":"From Shallow to Deep: Pinning Semantic Intent via Causal GRPO","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2605.28467","title":"Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.07808","title":"Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.04645","title":"Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2607.27594","title":"Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters","created":"2026-07-30","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":"2609.08186","title":"Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models","created":"2026-09-08","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":"2610.18566","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}