{"total":107,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"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":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156,"area":"safety"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"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":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"area":"lr"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58,"area":null},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"id":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","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":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27,"area":"safety"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2402.11725","title":"How Susceptible are Large Language Models to Ideological Manipulation?","created":"2024-02-18","cited_by_count":26,"area":null},{"id":"2406.01946","title":"Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature","created":"2024-06-04","cited_by_count":25,"area":"safety"},{"id":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2501.02968","title":"FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models","created":"2025-01-06","cited_by_count":25,"area":"rag"},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2409.17143","title":"Attention Prompting on Image for Large Vision-Language Models","created":"2024-09-25","cited_by_count":23,"area":"mllm"},{"id":"2402.05864","title":"Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs","created":"2024-02-08","cited_by_count":22,"area":"safety"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2502.03052","title":"Understanding and Enhancing the Transferability of Jailbreaking Attacks","created":"2025-02-05","cited_by_count":22,"area":"safety"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2405.14488","title":"MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"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":"2408.04568","title":"Learning Fine-Grained Grounded Citations for Attributed Large Language Models","created":"2024-08-08","cited_by_count":13,"area":null},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2407.13757","title":"Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-07-18","cited_by_count":11,"area":"rag"},{"id":"2410.06809","title":"Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level","created":"2024-10-09","cited_by_count":11,"area":"safety"},{"id":"2502.01349","title":"Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations","created":"2025-02-03","cited_by_count":11,"area":null},{"id":"2411.04223","title":"Diversity Helps Jailbreak Large Language Models","created":"2024-11-06","cited_by_count":10,"area":"safety"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2502.08142","title":"Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences","created":"2025-02-12","cited_by_count":8,"area":"safety"},{"id":"2607.26246","title":"Weak-to-Strong On-Policy Distillation","created":"2026-07-28","cited_by_count":8,"area":"distill"},{"id":"2412.12722","title":"Defending LVLMs Against Vision Attacks through Partial-Perception Supervision","created":"2024-12-17","cited_by_count":7,"area":"mllm"},{"id":"2412.18171","title":"Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models","created":"2024-12-24","cited_by_count":7,"area":"safety"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2506.00668","title":"SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues","created":"2025-05-31","cited_by_count":7,"area":"lr"},{"id":"2510.05052","title":"Proactive defense against LLM Jailbreak","created":"2025-10-06","cited_by_count":7,"area":"alignment"},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2510.24034","title":"AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts","created":"2025-10-28","cited_by_count":6,"area":"safety"},{"id":"2410.09804","title":"BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models","created":"2024-10-13","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":"2502.04643","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","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":"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":"2412.08201","title":"Model-Editing-Based Jailbreak against Safety-aligned Large Language Models","created":"2024-12-11","cited_by_count":4,"area":"alignment"},{"id":"2505.17089","title":"Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"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":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2602.01025","title":"Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models","created":"2026-02-01","cited_by_count":4,"area":"mllm"},{"id":"2603.20198","title":"Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning","created":"2026-02-05","cited_by_count":4,"area":"agents"},{"id":"2502.12630","title":"Automating Prompt Leakage Attacks on Large Language Models Using Agentic Approach","created":"2025-02-18","cited_by_count":3,"area":"agents"},{"id":"2505.11790","title":"JULI: Jailbreak Large Language Models by Self-Introspection","created":"2025-05-17","cited_by_count":3,"area":"alignment"},{"id":"2506.07402","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","created":"2025-06-09","cited_by_count":3,"area":"alignment"},{"id":"2510.06594","title":"Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?","created":"2025-10-08","cited_by_count":3,"area":"safety"},{"id":"2602.11096","title":"Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away","created":"2026-02-11","cited_by_count":3,"area":"lr"},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2605.00424","title":"Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes","created":"2026-05-01","cited_by_count":3,"area":"agents"},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2508.02997","title":"CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors","created":"2025-08-05","cited_by_count":2,"area":"safety"},{"id":"2510.13982","title":"Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations","created":"2025-10-15","cited_by_count":2,"area":"agents"},{"id":"2602.10179","title":"When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models","created":"2026-02-10","cited_by_count":2,"area":"safety"},{"id":"2603.22094","title":"Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2604.06436","title":"The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?","created":"2026-04-07","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":"2504.01533","title":"LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution","created":"2025-04-02","cited_by_count":1,"area":"safety"},{"id":"2506.18543","title":"SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models","created":"2025-06-23","cited_by_count":1,"area":"safety"},{"id":"2508.03054","title":"Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning","created":"2025-08-05","cited_by_count":1,"area":"lr"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2601.16506","title":"SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2603.00565","title":"MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs","created":"2026-02-28","cited_by_count":1,"area":"mllm"},{"id":"2603.22829","title":"Improving Safety Alignment via Balanced Direct Preference Optimization","created":"2026-03-24","cited_by_count":1,"area":"alignment"},{"id":"2603.23269","title":"Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2604.01444","title":"Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2604.25921","title":"One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2606.22686","title":"The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs","created":"2026-06-21","cited_by_count":1,"area":"alignment"},{"id":"2606.25592","title":"VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2406.11682","title":"Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":"safety"},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.07167","title":"Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models","created":"2025-05-12","cited_by_count":0,"area":"safety"},{"id":"2506.24056","title":"Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness","created":"2025-06-30","cited_by_count":0,"area":"alignment"},{"id":"2509.12221","title":"MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors","created":"2025-09-04","cited_by_count":0,"area":"alignment"},{"id":"2512.05518","title":"Matching Ranks Over Probability Yields Truly Deep Safety Alignment","created":"2025-12-05","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}