{"total":46,"rows":[{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18,"area":"safety"},{"id":"2510.19422","title":"LLM Unlearning with LLM Beliefs","created":"2025-10-22","cited_by_count":17,"area":"safety"},{"id":"2511.10222","title":"Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard","created":"2025-11-13","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":"2510.02286","title":"Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks","created":"2025-10-02","cited_by_count":8,"area":"safety"},{"id":"2605.01687","title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","created":"2026-05-03","cited_by_count":8,"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":"2512.03771","title":"In-Context Representation Hijacking","created":"2025-12-03","cited_by_count":5,"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":"2510.02999","title":"NonTextual Target Attack","created":"2025-10-03","cited_by_count":3,"area":"safety"},{"id":"2510.17277","title":"PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","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":"2601.11314","title":"Membership Inference on LLMs in the Wild","created":"2026-01-16","cited_by_count":3,"area":"safety"},{"id":"2604.14604","title":"Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection","created":"2026-04-16","cited_by_count":3,"area":"safety"},{"id":"2605.11002","title":"MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks","created":"2026-05-10","cited_by_count":3,"area":"safety"},{"id":"2605.18168","title":"Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models","created":"2026-05-18","cited_by_count":3,"area":"safety"},{"id":"2606.27379","title":"Position: The Term \"Machine Unlearning\" Is Overused in LLMs","created":"2026-05-08","cited_by_count":3,"area":"safety"},{"id":"2601.13607","title":"When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models","created":"2026-01-20","cited_by_count":2,"area":"safety"},{"id":"2602.03787","title":"Inference-time Unlearning Using Conformal Prediction","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2606.30783","title":"Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense","created":"2026-06-29","cited_by_count":2,"area":"safety"},{"id":"2507.22160","title":"Strategic Deflection: Defending LLMs from Logit Manipulation","created":"2025-07-29","cited_by_count":1,"area":"safety"},{"id":"2510.09689","title":"When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models","created":"2025-10-09","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":"2511.08367","title":"Why Does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs","created":"2025-11-11","cited_by_count":1,"area":"safety"},{"id":"2512.07038","title":"Ideal Attribution and Faithful Watermarks for Language Models","created":"2025-12-07","cited_by_count":1,"area":"safety"},{"id":"2601.09321","title":"SpatialJB: How Text Distribution Art Becomes the \"Jailbreak Key\" for LLM Guardrails","created":"2026-01-14","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":"2605.19227","title":"Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models","created":"2026-05-19","cited_by_count":1,"area":"safety"},{"id":"2606.04483","title":"Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenres","created":"2026-06-03","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":"2508.13246","title":"Involuntary Jailbreak: On Self-Prompting Attacks","created":"2025-08-18","cited_by_count":0,"area":"safety"},{"id":"2509.24624","title":"PRIVMARK: Private Large Language Models Watermarking with MPC","created":"2025-09-29","cited_by_count":0,"area":"safety"},{"id":"2511.17666","title":"Evaluating Adversarial Vulnerabilities in Modern Large Language Models","created":"2025-11-21","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":"2512.13703","title":"Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models","created":"2025-12-05","cited_by_count":0,"area":"safety"},{"id":"2601.04275","title":"Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs","created":"2026-01-07","cited_by_count":0,"area":"safety"},{"id":"2601.12937","title":"On the Evidentiary Limits of Membership Inference for Copyright Auditing","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.01752","title":"WorldCup Sampling for Multi-bit LLM Watermarking","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.09629","title":"Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks","created":"2026-02-10","cited_by_count":0,"area":"safety"},{"id":"2603.16192","title":"Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models","created":"2026-03-17","cited_by_count":0,"area":"safety"},{"id":"2604.12232","title":"TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs","created":"2026-04-14","cited_by_count":0,"area":"safety"},{"id":"2608.30362","title":"Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.02172","title":"Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search","created":"2026-09-02","cited_by_count":0,"area":"safety"},{"id":"2609.27378","title":"Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models","created":"2026-09-23","cited_by_count":0,"area":"safety"}],"next_cursor":null}