{"total":116,"rows":[{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2505.18333","title":"A Critical Evaluation of Defenses against Prompt Injection Attacks","created":"2025-05-23","cited_by_count":36,"area":"safety"},{"id":"2505.11413","title":"CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs","created":"2025-05-16","cited_by_count":26,"area":"safety"},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2503.10566","title":"ASIDE: Architectural Separation of Instructions and Data in Language Models","created":"2025-03-13","cited_by_count":24,"area":"safety"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2502.21059","title":"FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts","created":"2025-02-28","cited_by_count":18,"area":"safety"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","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":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2505.16934","title":"In-Context Watermarks for Large Language Models","created":"2025-05-22","cited_by_count":10,"area":"safety"},{"id":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","cited_by_count":10,"area":"safety"},{"id":"2506.12880","title":"Universal Jailbreak Suffixes Are Strong Attention Hijackers","created":"2025-06-15","cited_by_count":10,"area":"safety"},{"id":"2501.15570","title":"ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer","created":"2025-01-26","cited_by_count":9,"area":"safety"},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2506.07121","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","created":"2025-06-08","cited_by_count":9,"area":"safety"},{"id":"2505.12060","title":"Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement","created":"2025-05-17","cited_by_count":8,"area":"safety"},{"id":"2507.21134","title":"TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law","created":"2025-07-22","cited_by_count":8,"area":"safety"},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2508.08211","title":"SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders","created":"2025-08-11","cited_by_count":7,"area":"safety"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"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":"2502.15010","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","created":"2025-02-20","cited_by_count":5,"area":"safety"},{"id":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","cited_by_count":5,"area":"safety"},{"id":"2505.15656","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2505.22037","title":"Jailbreak Distillation: Renewable Safety Benchmarking","created":"2025-05-28","cited_by_count":5,"area":"safety"},{"id":"2507.04365","title":"Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs","created":"2025-07-06","cited_by_count":5,"area":"safety"},{"id":"2509.22263","title":"Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning","created":"2025-09-26","cited_by_count":5,"area":"safety"},{"id":"2605.12456","title":"TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection","created":"2026-05-12","cited_by_count":5,"area":"safety"},{"id":"2503.24191","title":"When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output","created":"2025-03-31","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":"2505.06027","title":"Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation","created":"2025-05-09","cited_by_count":4,"area":"safety"},{"id":"2505.13500","title":"Noise Injection Systemically Degrades Large Language Model Safety Guardrails","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2506.17299","title":"Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem","created":"2025-06-17","cited_by_count":4,"area":"safety"},{"id":"2508.12072","title":"Mitigating Jailbreaks with Intent-Aware LLMs","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2602.10568","title":"Gauss-Newton Unlearning for the LLM Era","created":"2026-02-11","cited_by_count":4,"area":"safety"},{"id":"2508.15847","title":"Mechanistic Exploration of Backdoored Large Language Model Attention Patterns","created":"2025-08-19","cited_by_count":3,"area":"safety"},{"id":"2510.15106","title":"PoTS: Proof-of-Training-Steps for Backdoor Detection in Large Language Models","created":"2025-10-16","cited_by_count":3,"area":"safety"},{"id":"2511.16278","title":"\"To Survive, I Must Defect\": Jailbreaking LLMs via the Game-Theory Scenarios","created":"2025-11-20","cited_by_count":3,"area":"safety"},{"id":"2512.16292","title":"In-Context Probing for Membership Inference in Fine-Tuned Language Models","created":"2025-12-18","cited_by_count":3,"area":"safety"},{"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":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2605.08778","title":"Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking","created":"2026-05-09","cited_by_count":3,"area":"safety"},{"id":"2608.16465","title":"JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills","created":"2026-08-17","cited_by_count":3,"area":"safety"},{"id":"2503.22539","title":"Efficient Verified Machine Unlearning For Distillation","created":"2025-03-28","cited_by_count":2,"area":"safety"},{"id":"2505.16643","title":"From Evaluation to Defense: Advancing Safety in Video Large Language Models","created":"2025-05-22","cited_by_count":2,"area":"safety"},{"id":"2505.19766","title":"PAM: Training Policy-Aligned Moderation Filters at Scale","created":"2025-05-26","cited_by_count":2,"area":"safety"},{"id":"2507.01693","title":"GPT, But Backwards: Exactly Inverting Language Model Outputs","created":"2025-07-02","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":"2606.08044","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","created":"2026-06-06","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":"2505.00843","title":"OET: Optimization-based prompt injection Evaluation Toolkit","created":"2025-05-01","cited_by_count":1,"area":"safety"},{"id":"2506.13494","title":"Watermarking LLM-Generated Datasets in Downstream Tasks","created":"2025-06-16","cited_by_count":1,"area":"safety"},{"id":"2507.00026","title":"RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2507.07056","title":"LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing","created":"2025-07-05","cited_by_count":1,"area":"safety"},{"id":"2511.07107","title":"MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs","created":"2025-11-10","cited_by_count":1,"area":"safety"},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2603.08234","title":"The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs","created":"2026-03-09","cited_by_count":1,"area":"safety"},{"id":"2603.21975","title":"SecureBreak -- A dataset towards safe and secure models","created":"2026-03-23","cited_by_count":1,"area":"safety"},{"id":"2604.12817","title":"Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory","created":"2026-04-14","cited_by_count":1,"area":"safety"},{"id":"2604.27666","title":"VOW: Verifiable and Oblivious Watermark Detection for Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"safety"},{"id":"2605.00553","title":"Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"id":"2605.12290","title":"Targeted Neuron Modulation via Contrastive Pair Search","created":"2026-05-12","cited_by_count":1,"area":"safety"},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2606.04027","title":"MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models","created":"2026-06-01","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":"2606.19887","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":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2607.13003","title":"Watermark Forensics for Generative Models: An Information-Theoretic Perspective","created":"2026-07-14","cited_by_count":1,"area":"safety"},{"id":"2607.18056","title":"An Early Warning of Emerging Biosecurity Risks in Frontier LLMs","created":"2026-07-20","cited_by_count":1,"area":"safety"},{"id":"2607.27081","title":"On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment","created":"2026-07-29","cited_by_count":1,"area":"safety"},{"id":"2608.20047","title":"Auditing Cross-Lingual Fairness in Language Model Watermarking","created":"2026-08-20","cited_by_count":1,"area":"safety"},{"id":"2608.23028","title":"PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies","created":"2026-08-24","cited_by_count":1,"area":"safety"},{"id":"2608.27666","title":"Semantic Watermarking with Order-Robust Detection over Sub-sentence Units","created":"2026-08-27","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":"2505.11835","title":"Multilingual Collaborative Defense for Large Language Models","created":"2025-05-17","cited_by_count":0,"area":"safety"},{"id":"2512.13352","title":"On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2602.04893","title":"A Causal Perspective for Enhancing Jailbreak Attack and Defense","created":"2026-01-31","cited_by_count":0,"area":"safety"},{"id":"2602.23798","title":"MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"safety"},{"id":"2605.00364","title":"Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.11612","title":"When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.19147","title":"Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks","created":"2026-05-18","cited_by_count":0,"area":"safety"},{"id":"2605.19377","title":"The Evaluation Game: Beyond Static LLM Benchmarking","created":"2026-05-19","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":"2605.29629","title":"Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.11817","title":"Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2607.05353","title":"Selective Disclosure Watermarking for Large Language Models","created":"2026-07-06","cited_by_count":0,"area":"safety"},{"id":"2607.15218","title":"When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space","created":"2026-07-16","cited_by_count":0,"area":"safety"},{"id":"2607.23015","title":"Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks","created":"2026-07-25","cited_by_count":0,"area":"safety"},{"id":"2608.09900","title":"Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2608.17360","title":"Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets","created":"2026-08-18","cited_by_count":0,"area":"safety"},{"id":"2609.02177","title":"WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading","created":"2026-09-02","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}