{"total":85,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032,"area":"safety"},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70,"area":"safety"},{"id":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69,"area":"safety"},{"id":"2403.12171","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","created":"2024-03-18","cited_by_count":60,"area":"safety"},{"id":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2408.04686","title":"Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles","created":"2024-08-08","cited_by_count":56,"area":"safety"},{"id":"2502.19820","title":"Foot-In-The-Door: A Multi-turn Jailbreak for LLMs","created":"2025-02-27","cited_by_count":54,"area":"safety"},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51,"area":"safety"},{"id":"2406.09289","title":"Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models","created":"2024-06-13","cited_by_count":37,"area":"safety"},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2412.05934","title":"Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models","created":"2024-12-08","cited_by_count":33,"area":"safety"},{"id":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30,"area":"safety"},{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2604.09378","title":"BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning","created":"2026-04-10","cited_by_count":27,"area":"safety"},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"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":"2411.16736","title":"ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain","created":"2024-11-23","cited_by_count":15,"area":"safety"},{"id":"2412.16633","title":"Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots","created":"2024-12-21","cited_by_count":15,"area":"safety"},{"id":"2507.00841","title":"SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents","created":"2025-07-01","cited_by_count":15,"area":"safety"},{"id":"2406.03805","title":"AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens","created":"2024-06-06","cited_by_count":14,"area":"safety"},{"id":"2506.05735","title":"Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness","created":"2025-06-06","cited_by_count":14,"area":"safety"},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13,"area":"safety"},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2503.09117","title":"GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs","created":"2025-03-12","cited_by_count":12,"area":"safety"},{"id":"2503.01865","title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints","created":"2025-02-25","cited_by_count":11,"area":"safety"},{"id":"2505.16947","title":"MixAT: Combining Continuous and Discrete Adversarial Training for LLMs","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2506.12551","title":"MEraser: An Effective Fingerprint Erasure Approach for Large Language Models","created":"2025-06-14","cited_by_count":11,"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":"2505.02862","title":"Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs","created":"2025-05-03","cited_by_count":9,"area":"safety"},{"id":"2505.13541","title":"SPIRIT: Patching Speech Language Models against Jailbreak Attacks","created":"2025-05-18","cited_by_count":9,"area":"safety"},{"id":"2405.03654","title":"Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent","created":"2024-05-06","cited_by_count":8,"area":"safety"},{"id":"2510.17633","title":"SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering","created":"2025-10-20","cited_by_count":8,"area":"safety"},{"id":"2505.15753","title":"Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval","created":"2025-05-21","cited_by_count":7,"area":"safety"},{"id":"2606.14748","title":"Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2","created":"2026-06-05","cited_by_count":7,"area":"safety"},{"id":"2601.00590","title":"SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation","created":"2026-01-02","cited_by_count":6,"area":"safety"},{"id":"2505.14832","title":"SEPS: A Separability Measure for Robust Unlearning in LLMs","created":"2025-05-20","cited_by_count":5,"area":"safety"},{"id":"2403.10020","title":"Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs","created":"2024-03-15","cited_by_count":4,"area":"safety"},{"id":"2406.10847","title":"TorchOpera: A Compound AI System for LLM Safety","created":"2024-06-16","cited_by_count":4,"area":"safety"},{"id":"2502.15594","title":"SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention","created":"2025-02-21","cited_by_count":4,"area":"safety"},{"id":"2503.11324","title":"Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking","created":"2025-03-14","cited_by_count":4,"area":"safety"},{"id":"2508.15449","title":"Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","cited_by_count":4,"area":"safety"},{"id":"2605.06605","title":"How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation","created":"2026-05-07","cited_by_count":4,"area":"safety"},{"id":"2502.06567","title":"Membership Inference Risks in Quantized Models: A Theoretical and Empirical Study","created":"2025-02-10","cited_by_count":3,"area":"safety"},{"id":"2502.10487","title":"Fast Proxies for LLM Robustness Evaluation","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2502.16491","title":"Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models","created":"2025-02-23","cited_by_count":3,"area":"safety"},{"id":"2602.04581","title":"Trust The Typical","created":"2026-02-04","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":"2502.18518","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2502.19883","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","created":"2025-02-27","cited_by_count":2,"area":"safety"},{"id":"2503.05721","title":"What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets","created":"2025-02-17","cited_by_count":2,"area":"safety"},{"id":"2503.08990","title":"Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks","created":"2025-03-12","cited_by_count":2,"area":"safety"},{"id":"2505.01315","title":"Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System","created":"2025-05-02","cited_by_count":2,"area":"safety"},{"id":"2507.07735","title":"GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing","created":"2025-07-10","cited_by_count":2,"area":"safety"},{"id":"2508.16484","title":"HAMSA: Hijacking Aligned Compact Models via Stealthy Automation","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2506.01770","title":"ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2508.20443","title":"Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint","created":"2025-08-28","cited_by_count":1,"area":"safety"},{"id":"2510.01157","title":"Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2512.06655","title":"Graph-Regularized Sparse Autoencoders for LLM Safety Steering","created":"2025-12-07","cited_by_count":1,"area":"safety"},{"id":"2512.14751","title":"One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs","created":"2025-12-14","cited_by_count":1,"area":"safety"},{"id":"2602.03379","title":"Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures","created":"2026-02-03","cited_by_count":1,"area":"safety"},{"id":"2603.29038","title":"Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning","created":"2026-03-30","cited_by_count":1,"area":"safety"},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2606.20553","title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","created":"2026-06-18","cited_by_count":1,"area":"safety"},{"id":"2505.24536","title":"CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control","created":"2025-05-30","cited_by_count":0,"area":"safety"},{"id":"2511.05532","title":"Beyond One-Size-Fits-All: Personalized Harmful Content Detection with In-Context Learning","created":"2025-10-29","cited_by_count":0,"area":"safety"},{"id":"2512.04841","title":"SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security","created":"2025-12-04","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":"2602.04893","title":"A Causal Perspective for Enhancing Jailbreak Attack and Defense","created":"2026-01-31","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":"2605.08898","title":"LLM-Agnostic Semantic Representation Attack","created":"2026-05-09","cited_by_count":0,"area":"safety"},{"id":"2605.13411","title":"Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2605.17128","title":"New Wide-Net-Casting Jailbreak Attacks Risk Large Models","created":"2026-05-16","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":"2605.28632","title":"Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2605.29667","title":"Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.09388","title":"Distilling Safe LLM Systems via Soft Prompts for On Device Settings","created":"2026-06-08","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":"2609.05117","title":"TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors","created":"2026-09-04","cited_by_count":0,"area":"safety"},{"id":"2609.20129","title":"Local Sparsity Enables Unsupervised LLM Safety Detection","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.32602","title":"AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion","created":"2026-09-26","cited_by_count":0,"area":"safety"}],"next_cursor":null}