{"total":135,"rows":[{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"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":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37,"area":"safety"},{"id":"2511.20597","title":"BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents","created":"2025-11-25","cited_by_count":24,"area":"safety"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2603.06594","title":"A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness","created":"2026-02-04","cited_by_count":20,"area":"safety"},{"id":"2510.05244","title":"Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?","created":"2025-10-06","cited_by_count":18,"area":"safety"},{"id":"2603.13026","title":"PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses","created":"2026-03-13","cited_by_count":16,"area":"safety"},{"id":"2509.10248","title":"Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications","created":"2025-09-12","cited_by_count":13,"area":"safety"},{"id":"2602.22983","title":"Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search","created":"2026-02-26","cited_by_count":13,"area":"safety"},{"id":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2509.01444","title":"Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions","created":"2025-09-01","cited_by_count":11,"area":"safety"},{"id":"2512.21008","title":"GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs","created":"2025-12-24","cited_by_count":11,"area":"safety"},{"id":"2604.08499","title":"PIArena: A Platform for Prompt Injection Evaluation","created":"2026-04-09","cited_by_count":11,"area":"safety"},{"id":"2510.09694","title":"Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection","created":"2025-10-09","cited_by_count":9,"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":"2510.21910","title":"Adversarial D\\'ej\\`a Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks","created":"2025-10-24","cited_by_count":7,"area":"safety"},{"id":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2604.01194","title":"AgentWatcher: A Rule-based Prompt Injection Monitor","created":"2026-04-01","cited_by_count":6,"area":"safety"},{"id":"2510.07239","title":"Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts","created":"2025-10-08","cited_by_count":5,"area":"safety"},{"id":"2505.18556","title":"Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation","created":"2025-05-24","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":"2510.00761","title":"Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2602.08741","title":"Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing","created":"2026-02-09","cited_by_count":4,"area":"safety"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2604.08169","title":"Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2506.16792","title":"MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning","created":"2025-06-20","cited_by_count":3,"area":"safety"},{"id":"2510.17620","title":"Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models","created":"2025-10-20","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":"2601.05339","title":"Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models","created":"2026-01-08","cited_by_count":3,"area":"safety"},{"id":"2601.08490","title":"BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2602.07235","title":"ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport","created":"2026-02-06","cited_by_count":3,"area":"safety"},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","cited_by_count":3,"area":"safety"},{"id":"2604.14865","title":"Segment-Level Coherence for Robust Harmful Intent Probing in LLMs","created":"2026-04-16","cited_by_count":3,"area":"safety"},{"id":"2604.22134","title":"SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs","created":"2026-04-24","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":"2508.04281","title":"Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy","created":"2025-08-06","cited_by_count":2,"area":"safety"},{"id":"2509.20924","title":"RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks","created":"2025-09-25","cited_by_count":2,"area":"safety"},{"id":"2601.05466","title":"Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning","created":"2026-01-09","cited_by_count":2,"area":"safety"},{"id":"2603.10913","title":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2604.11546","title":"RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience","created":"2026-04-13","cited_by_count":2,"area":"safety"},{"id":"2605.05443","title":"SLAM: Structural Linguistic Activation Marking for Language Models","created":"2026-05-06","cited_by_count":2,"area":"safety"},{"id":"2606.05609","title":"SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks","created":"2026-06-04","cited_by_count":2,"area":"safety"},{"id":"2606.07688","title":"TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation","created":"2026-06-05","cited_by_count":2,"area":"safety"},{"id":"2606.19535","title":"FloatDoor: Platform-Triggered Backdoors in LLMs","created":"2026-06-17","cited_by_count":2,"area":"safety"},{"id":"2608.08027","title":"BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes","created":"2026-08-08","cited_by_count":2,"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":"2510.14470","title":"Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models","created":"2025-10-16","cited_by_count":1,"area":"safety"},{"id":"2602.06440","title":"TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2602.12318","title":"Abstractive Red-Teaming of Language Model Character","created":"2026-02-12","cited_by_count":1,"area":"safety"},{"id":"2602.18583","title":"Luna-2: Scalable Single-Token Evaluation with Small Language Models","created":"2026-02-20","cited_by_count":1,"area":"safety"},{"id":"2603.02262","title":"Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs","created":"2026-02-28","cited_by_count":1,"area":"safety"},{"id":"2603.05921","title":"BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation","created":"2026-03-06","cited_by_count":1,"area":"safety"},{"id":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","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":"2605.00689","title":"BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"id":"2605.09070","title":"Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","cited_by_count":1,"area":"safety"},{"id":"2605.25073","title":"Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions","created":"2026-05-24","cited_by_count":1,"area":"safety"},{"id":"2605.29434","title":"AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2606.02640","title":"D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting","created":"2026-05-31","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":"2606.09890","title":"PreAct-Bench: Benchmarking Predictive Monitoring in LLMs","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":"2606.11425","title":"JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization","created":"2026-06-09","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":"2608.03201","title":"When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models","created":"2026-08-04","cited_by_count":1,"area":"safety"},{"id":"2608.14906","title":"Optimal Watermark Localization in Mixed-Source Large Language Model Texts","created":"2026-08-14","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":"2609.16204","title":"Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration","created":"2026-09-14","cited_by_count":1,"area":"safety"},{"id":"2512.00837","title":"WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking","created":"2025-11-30","cited_by_count":0,"area":"safety"},{"id":"2512.04044","title":"MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2512.13703","title":"Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models","created":"2025-12-05","cited_by_count":0,"area":"safety"},{"id":"2512.16182","title":"DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack","created":"2025-12-18","cited_by_count":0,"area":"safety"},{"id":"2601.13359","title":"Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.02139","title":"EvoMU: Evolutionary Machine Unlearning","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.16752","title":"The Vulnerability of LLM Rankers to Prompt Injection Attacks","created":"2026-02-18","cited_by_count":0,"area":"safety"},{"id":"2604.15967","title":"When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2604.24162","title":"Defusing the Trigger: Tail-Risk-Informed Attention Rebalancing for LLM Backdoor Mitigation","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2604.24983","title":"Adaptive Prompt Embedding Optimization for LLM Jailbreaking","created":"2026-04-27","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":"2605.07032","title":"A Systematic Investigation of RL-Jailbreaking in LLMs","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.08898","title":"LLM-Agnostic Semantic Representation Attack","created":"2026-05-09","cited_by_count":0,"area":"safety"},{"id":"2605.10582","title":"Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing","created":"2026-05-11","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":"2605.11996","title":"BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.18879","title":"ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2605.25510","title":"The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models","created":"2026-05-25","cited_by_count":0,"area":"safety"},{"id":"2605.30919","title":"De-attribute to Forget for LLM Unlearning","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2606.00654","title":"The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction","created":"2026-05-30","cited_by_count":0,"area":"safety"},{"id":"2606.11202","title":"One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection","created":"2026-04-22","cited_by_count":0,"area":"safety"},{"id":"2606.18309","title":"SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector","created":"2026-06-16","cited_by_count":0,"area":"safety"},{"id":"2606.22878","title":"Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2606.27632","title":"Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2606.31309","title":"CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs","created":"2026-06-30","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}