{"list":"other","total":192,"rows":[{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2311.04892","title":"Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs","created":"2023-11-08","cited_by_count":199},{"id":"2410.05295","title":"AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs","created":"2024-10-03","cited_by_count":199},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"2504.11703","title":"Progent: Securing AI Agents with Privilege Control","created":"2025-04-16","cited_by_count":141},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130},{"id":"2403.04960","title":"IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems","created":"2024-03-08","cited_by_count":130},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126},{"id":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125},{"id":"2505.23643","title":"Securing AI Agents with Information-Flow Control","created":"2025-05-29","cited_by_count":121},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113},{"id":"2402.11746","title":"Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic","created":"2024-02-19","cited_by_count":112},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110},{"id":"2409.19091","title":"System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective","created":"2024-09-27","cited_by_count":96},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90},{"id":"2502.11448","title":"AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection","created":"2025-02-17","cited_by_count":89},{"id":"2410.11779","title":"MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation","created":"2024-10-15","cited_by_count":88},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63},{"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},{"id":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52},{"id":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51},{"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},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46},{"id":"2305.14928","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","created":"2023-05-24","cited_by_count":45},{"id":"2502.17598","title":"Hallucination Detection in LLMs Using Spectral Features of Attention Maps","created":"2025-02-24","cited_by_count":43},{"id":"2405.18654","title":"Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment","created":"2024-05-28","cited_by_count":42},{"id":"2508.06601","title":"Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs","created":"2025-08-08","cited_by_count":42},{"id":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41},{"id":"2312.00027","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","created":"2023-11-15","cited_by_count":39},{"id":"2403.18346","title":"Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective","created":"2024-03-27","cited_by_count":39},{"id":"2504.09466","title":"AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender","created":"2025-04-13","cited_by_count":38},{"id":"2508.08127","title":"BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks","created":"2025-08-11","cited_by_count":38},{"id":"2006.14042","title":"Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks","created":"2020-06-24","cited_by_count":37},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37},{"id":"2403.01251","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","created":"2024-03-02","cited_by_count":37},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35},{"id":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35},{"id":"2406.07594","title":"MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models","created":"2024-06-11","cited_by_count":34},{"id":"2504.00218","title":"$\\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks","created":"2025-03-31","cited_by_count":34},{"id":"2505.04806","title":"Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs","created":"2025-05-07","cited_by_count":34},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33},{"id":"2406.12232","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","created":"2024-06-18","cited_by_count":33},{"id":"2309.01686","title":"MathAttack: Attacking Large Language Models Towards Math Solving Ability","created":"2023-09-04","cited_by_count":32},{"id":"2403.14952","title":"Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation","created":"2024-03-22","cited_by_count":32},{"id":"2408.02946","title":"Scaling Trends for Data Poisoning in LLMs","created":"2024-08-06","cited_by_count":30},{"id":"2408.09429","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","created":"2024-08-18","cited_by_count":30},{"id":"2406.16449","title":"Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models","created":"2024-06-24","cited_by_count":29},{"id":"2310.12516","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","created":"2023-10-19","cited_by_count":28},{"id":"2601.11044","title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","created":"2026-01-16","cited_by_count":28},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25},{"id":"2406.06369","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","created":"2024-06-10","cited_by_count":23},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21},{"id":"2406.15484","title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","created":"2024-06-17","cited_by_count":21},{"id":"2409.14866","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","created":"2024-09-23","cited_by_count":21},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21},{"id":"2506.17088","title":"Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation","created":"2025-06-20","cited_by_count":21},{"id":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20},{"id":"2406.05344","title":"MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention","created":"2024-06-08","cited_by_count":20},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20},{"id":"2505.19933","title":"Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making","created":"2025-05-26","cited_by_count":20},{"id":"2410.12662","title":"Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models","created":"2024-10-16","cited_by_count":19},{"id":"2502.11598","title":"Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?","created":"2025-02-17","cited_by_count":19},{"id":"2503.00137","title":"SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models","created":"2025-02-28","cited_by_count":19}],"next_cursor":"100"}