{"total":129,"rows":[{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2503.03480","title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","created":"2025-03-05","cited_by_count":72,"area":"vla"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31,"area":"lr"},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2505.11842","title":"Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs","created":"2025-05-17","cited_by_count":28,"area":"mllm"},{"id":"2508.01710","title":"CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications","created":"2025-08-03","cited_by_count":27,"area":"agents"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"area":"agents"},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19,"area":"lr"},{"id":"2509.02563","title":"DynaGuard: A Dynamic Guardian Model With User-Defined Policies","created":"2025-09-02","cited_by_count":19,"area":"safety"},{"id":"2502.00937","title":"ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving","created":"2025-02-02","cited_by_count":18,"area":"mllm"},{"id":"2510.22300","title":"T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model","created":"2025-10-25","cited_by_count":17,"area":null},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16,"area":"mllm"},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2508.12815","title":"Learning to Steer: Input-dependent Steering for Multimodal LLMs","created":"2025-08-18","cited_by_count":15,"area":"mllm"},{"id":"2501.10057","title":"MSTS: A Multimodal Safety Test Suite for Vision-Language Models","created":"2025-01-17","cited_by_count":12,"area":"mllm"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2505.23793","title":"USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models","created":"2025-05-26","cited_by_count":10,"area":"mllm"},{"id":"2504.16907","title":"BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation","created":"2025-04-23","cited_by_count":9,"area":"safety"},{"id":"2506.04704","title":"HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model","created":"2025-06-05","cited_by_count":9,"area":"mllm"},{"id":"2506.14493","title":"LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops","created":"2025-06-17","cited_by_count":9,"area":"mllm"},{"id":"2510.09694","title":"Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection","created":"2025-10-09","cited_by_count":9,"area":"safety"},{"id":"2604.13954","title":"HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark","created":"2026-04-15","cited_by_count":9,"area":"agents"},{"id":"2510.18214","title":"VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2505.14035","title":"ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2505.23856","title":"OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2507.10069","title":"ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism","created":"2025-07-14","cited_by_count":7,"area":"mllm"},{"id":"2507.15339","title":"LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators","created":"2025-07-21","cited_by_count":7,"area":null},{"id":"2510.03417","title":"NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks","created":"2025-10-03","cited_by_count":7,"area":"safety"},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2512.02306","title":"OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning","created":"2025-12-02","cited_by_count":7,"area":"lr"},{"id":"2602.23636","title":"FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation","created":"2026-02-27","cited_by_count":7,"area":null},{"id":"2502.07987","title":"Universal Adversarial Attack on Aligned Multimodal LLMs","created":"2025-02-11","cited_by_count":6,"area":"mllm"},{"id":"2505.16446","title":"Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2603.01228","title":"Towards Policy-Adaptive Image Guardrail: Benchmark and Method","created":"2026-03-01","cited_by_count":6,"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":"2504.20376","title":"When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems","created":"2025-04-29","cited_by_count":5,"area":"safety"},{"id":"2510.13190","title":"SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2511.11301","title":"EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment","created":"2025-11-14","cited_by_count":5,"area":"lr"},{"id":"2505.12368","title":"CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement","created":"2025-05-18","cited_by_count":4,"area":"safety"},{"id":"2505.16104","title":"Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models","created":"2025-05-22","cited_by_count":4,"area":"mllm"},{"id":"2507.22037","title":"Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security","created":"2025-07-29","cited_by_count":4,"area":"mllm"},{"id":"2510.17687","title":"CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks","created":"2025-10-20","cited_by_count":4,"area":"lr"},{"id":"2511.00382","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2511.20994","title":"GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision","created":"2025-11-26","cited_by_count":4,"area":"lr"},{"id":"2512.18027","title":"CoPE: A Small Language Model for Steerable and Scalable Content Labeling","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2603.02219","title":"NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels","created":"2026-02-10","cited_by_count":4,"area":"mechinterp"},{"id":"2603.17372","title":"Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift","created":"2026-03-18","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":"2605.15030","title":"WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2502.08657","title":"Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions","created":"2025-02-08","cited_by_count":3,"area":"alignment"},{"id":"2509.24090","title":"Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2511.12497","title":"SGuard-v1: Safety Guardrail for Large Language Models","created":"2025-11-16","cited_by_count":3,"area":"safety"},{"id":"2511.16278","title":"\"To Survive, I Must Defect\": Jailbreaking LLMs via the Game-Theory Scenarios","created":"2025-11-20","cited_by_count":3,"area":"safety"},{"id":"2604.08867","title":"AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2604.12284","title":"WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2607.15550","title":"SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction","created":"2026-07-17","cited_by_count":3,"area":"wm"},{"id":"2504.09712","title":"The Structural Safety Generalization Problem","created":"2025-04-13","cited_by_count":2,"area":"safety"},{"id":"2506.02479","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2507.07146","title":"Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak","created":"2025-07-09","cited_by_count":2,"area":"safety"},{"id":"2509.04403","title":"Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios","created":"2025-09-04","cited_by_count":2,"area":"mllm"},{"id":"2509.15695","title":"ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models","created":"2025-09-19","cited_by_count":2,"area":"mllm"},{"id":"2509.23783","title":"Falcon: A Cross-Modal Evaluation Dataset for Comprehensive Safety Perception","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.10271","title":"MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation","created":"2025-10-11","cited_by_count":2,"area":"safety"},{"id":"2510.25179","title":"Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models","created":"2025-10-29","cited_by_count":2,"area":"mllm"},{"id":"2602.03328","title":"GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"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":"2604.00310","title":"CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment","created":"2026-03-31","cited_by_count":2,"area":"alignment"},{"id":"2606.02041","title":"SentGuard: Sentence-Level Streaming Guardrails for Large Language Models","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2505.03135","title":"Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2505.05619","title":"LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities","created":"2025-05-08","cited_by_count":1,"area":"safety"},{"id":"2509.18382","title":"Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints","created":"2025-09-22","cited_by_count":1,"area":"lr"},{"id":"2509.25896","title":"LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models","created":"2025-09-30","cited_by_count":1,"area":"mllm"},{"id":"2511.08484","title":"Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2601.03416","title":"GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"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":"2601.19507","title":"Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs","created":"2026-01-27","cited_by_count":1,"area":"mllm"},{"id":"2602.14399","title":"Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models","created":"2026-02-16","cited_by_count":1,"area":"mllm"},{"id":"2603.10010","title":"FERRET: Framework for Expansion Reliant Red Teaming","created":"2026-02-17","cited_by_count":1,"area":"safety"},{"id":"2603.27112","title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.00323","title":"Large Language Models in the Abuse Detection Pipeline","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.17053","title":"Jailbreaking Large Language Models with Morality Attacks","created":"2026-04-18","cited_by_count":1,"area":"safety"},{"id":"2606.05660","title":"Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.28153","title":"Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2607.21401","title":"When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2502.09175","title":"FLAME: Flexible LLM-Assisted Moderation Engine","created":"2025-02-13","cited_by_count":0,"area":"safety"},{"id":"2502.12411","title":"Gradient Co-occurrence Analysis for Detecting Unsafe Prompts in Large Language Models","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2506.03614","title":"VLMs Can Aggregate Scattered Training Patches","created":"2025-06-04","cited_by_count":0,"area":"mllm"},{"id":"2506.05368","title":"Speaking images. A novel framework for the automated self-description of artworks","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2509.21050","title":"GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutions","created":"2025-09-25","cited_by_count":0,"area":"lr"},{"id":"2509.26345","title":"SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2511.19537","title":"Cross-Domain Generalization of Multimodal LLMs for Global Photovoltaic Assessment","created":"2025-11-24","cited_by_count":0,"area":"mllm"},{"id":"2512.03087","title":"When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI","created":"2025-11-29","cited_by_count":0,"area":"mllm"},{"id":"2512.13703","title":"Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models","created":"2025-12-05","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}