{"total":160,"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":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264,"area":"safety"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2504.11358","title":"DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks","created":"2025-04-15","cited_by_count":143,"area":"safety"},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"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":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110,"area":"safety"},{"id":"2402.18104","title":"Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction","created":"2024-02-28","cited_by_count":107,"area":"safety"},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"area":"safety"},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2403.03792","title":"Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks","created":"2024-03-06","cited_by_count":85,"area":"safety"},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2310.18491","title":"Publicly-Detectable Watermarking for Language Models","created":"2023-10-27","cited_by_count":76,"area":"safety"},{"id":"2410.11143","title":"LLM Unlearning via Loss Adjustment with Only Forget Data","created":"2024-10-14","cited_by_count":75,"area":"safety"},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"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":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2401.13927","title":"Adaptive Text Watermark for Large Language Models","created":"2024-01-25","cited_by_count":67,"area":"safety"},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54,"area":"safety"},{"id":"2402.15911","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","created":"2024-02-24","cited_by_count":52,"area":"safety"},{"id":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2505.11953","title":"Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning","created":"2025-05-17","cited_by_count":39,"area":"safety"},{"id":"2402.09177","title":"Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks","created":"2024-02-14","cited_by_count":36,"area":"safety"},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","cited_by_count":34,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2404.06664","title":"CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge","created":"2024-04-10","cited_by_count":28,"area":"safety"},{"id":"2510.12252","title":"PromptLocate: Localizing Prompt Injection Attacks","created":"2025-10-14","cited_by_count":28,"area":"safety"},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","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":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2410.02890","title":"Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach","created":"2024-10-03","cited_by_count":22,"area":"safety"},{"id":"2502.03052","title":"Understanding and Enhancing the Transferability of Jailbreaking Attacks","created":"2025-02-05","cited_by_count":22,"area":"safety"},{"id":"2506.07596","title":"TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts","created":"2025-06-09","cited_by_count":19,"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":"2503.16023","title":"BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":17,"area":"safety"},{"id":"2510.21189","title":"Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency","created":"2025-10-24","cited_by_count":17,"area":"safety"},{"id":"2410.02099","title":"A Watermark for Black-Box Language Models","created":"2024-10-02","cited_by_count":16,"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":"2412.03235","title":"Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?","created":"2024-12-04","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":"2406.03805","title":"AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens","created":"2024-06-06","cited_by_count":14,"area":"safety"},{"id":"2410.13808","title":"De-mark: Watermark Removal in Large Language Models","created":"2024-10-17","cited_by_count":14,"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":"2410.18861","title":"Provably Robust Watermarks for Open-Source Language Models","created":"2024-10-24","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":"2406.10281","title":"Watermarking Language Models with Error Correcting Codes","created":"2024-06-12","cited_by_count":10,"area":"safety"},{"id":"2407.16318","title":"PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing","created":"2024-07-23","cited_by_count":10,"area":"safety"},{"id":"2410.16527","title":"Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis","created":"2024-10-21","cited_by_count":10,"area":"safety"},{"id":"2411.04223","title":"Diversity Helps Jailbreak Large Language Models","created":"2024-11-06","cited_by_count":10,"area":"safety"},{"id":"2407.08441","title":"Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation","created":"2024-07-11","cited_by_count":9,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"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":"2506.00359","title":"Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy","created":"2025-05-31","cited_by_count":9,"area":"safety"},{"id":"2408.09326","title":"Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks","created":"2024-08-18","cited_by_count":8,"area":"safety"},{"id":"2504.02080","title":"Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses","created":"2025-04-02","cited_by_count":8,"area":"safety"},{"id":"2405.02365","title":"ModelShield: Adaptive and Robust Watermark against Model Extraction Attack","created":"2024-05-03","cited_by_count":7,"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":"2506.02442","title":"Should LLM Safety Be More Than Refusing Harmful Instructions?","created":"2025-06-03","cited_by_count":7,"area":"safety"},{"id":"2603.13461","title":"Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference","created":"2026-03-13","cited_by_count":7,"area":"safety"},{"id":"2410.03600","title":"Efficiently Identifying Watermarked Segments in Mixed-Source Texts","created":"2024-10-04","cited_by_count":6,"area":"safety"},{"id":"2501.13677","title":"HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor","created":"2025-01-23","cited_by_count":6,"area":"safety"},{"id":"2505.14368","title":"From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6,"area":"safety"},{"id":"2509.24043","title":"An Ensemble Framework for Unbiased Language Model Watermarking","created":"2025-09-28","cited_by_count":6,"area":"safety"},{"id":"2405.15269","title":"Test-Time Multimodal Backdoor Detection by Contrastive Prompting","created":"2024-05-24","cited_by_count":5,"area":"safety"},{"id":"2502.01241","title":"Peering Behind the Shield: Guardrail Identification in Large Language Models","created":"2025-02-03","cited_by_count":5,"area":"safety"},{"id":"2503.11185","title":"Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks","created":"2025-03-14","cited_by_count":5,"area":"safety"},{"id":"2505.22298","title":"Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing","created":"2025-05-28","cited_by_count":5,"area":"safety"},{"id":"2509.24048","title":"Analyzing and Evaluating Unbiased Language Model Watermark","created":"2025-09-28","cited_by_count":5,"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":"2407.00075","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","created":"2024-06-21","cited_by_count":4,"area":"safety"},{"id":"2410.04190","title":"Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2411.01565","title":"SQL Injection Jailbreak: A Structural Disaster of Large Language Models","created":"2024-11-03","cited_by_count":4,"area":"safety"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2503.01926","title":"Unnatural Languages Are Not Bugs but Features for LLMs","created":"2025-03-02","cited_by_count":4,"area":"safety"},{"id":"2505.09820","title":"Adversarial Attack on Large Language Models using Exponentiated Gradient Descent","created":"2025-05-14","cited_by_count":4,"area":"safety"},{"id":"2507.07871","title":"Mitigating Watermark Forgery in Generative Models via Randomized Key Selection","created":"2025-07-10","cited_by_count":4,"area":"safety"},{"id":"2510.05025","title":"Imperceptible Jailbreaking against Large Language Models","created":"2025-10-06","cited_by_count":4,"area":"safety"},{"id":"2510.18728","title":"HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-10-21","cited_by_count":4,"area":"safety"},{"id":"2511.00030","title":"Probing Knowledge Holes in Unlearned LLMs","created":"2025-10-27","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":"2402.16889","title":"Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation","created":"2024-02-23","cited_by_count":3,"area":"safety"},{"id":"2406.02044","title":"Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA","created":"2024-06-04","cited_by_count":3,"area":"safety"},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","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"}],"next_cursor":"100"}