{"total":62,"rows":[{"id":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67,"area":"mllm"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35,"area":"mllm"},{"id":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29,"area":"lr"},{"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":"2511.10222","title":"Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard","created":"2025-11-13","cited_by_count":13,"area":"safety"},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12,"area":"mllm"},{"id":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2511.12982","title":"SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization","created":"2025-11-17","cited_by_count":12,"area":"lr"},{"id":"2508.05087","title":"JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2512.06589","title":"OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation","created":"2025-12-06","cited_by_count":11,"area":"safety"},{"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":"2505.14289","title":"EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks","created":"2025-05-20","cited_by_count":9,"area":"agents"},{"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":"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":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6,"area":"mllm"},{"id":"2508.19445","title":"On Surjectivity of Neural Networks: Can you elicit any behavior from your model?","created":"2025-08-26","cited_by_count":4,"area":null},{"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":"2603.27918","title":"Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey","created":"2026-03-30","cited_by_count":4,"area":"mllm"},{"id":"2605.00583","title":"Jailbreaking Vision-Language Models Through the Visual Modality","created":"2026-05-01","cited_by_count":4,"area":"mllm"},{"id":"2505.12287","title":"The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models","created":"2025-05-18","cited_by_count":3,"area":"safety"},{"id":"2510.17277","title":"PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2603.22882","title":"TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration","created":"2026-03-24","cited_by_count":3,"area":"mllm"},{"id":"2503.06989","title":"Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application","created":"2025-03-10","cited_by_count":2,"area":"mllm"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2509.05471","title":"Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models","created":"2025-09-05","cited_by_count":2,"area":"safety"},{"id":"2509.21401","title":"JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2510.01342","title":"Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach","created":"2025-10-01","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":"2605.26158","title":"Furina: Fragmented Uncertainty-Driven Refusal Instability Attack","created":"2026-05-24","cited_by_count":2,"area":"alignment"},{"id":"2607.09697","title":"Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs","created":"2026-06-20","cited_by_count":2,"area":"mllm"},{"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":"2510.15430","title":"Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models","created":"2025-10-17","cited_by_count":1,"area":"mllm"},{"id":"2510.17759","title":"VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2511.13892","title":"Jailbreaking Large Vision Language Models in Intelligent Transportation Systems","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2512.07141","title":"Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2601.05150","title":"$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models","created":"2026-01-08","cited_by_count":1,"area":"safety"},{"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":"2602.08136","title":"Robustness of Vision Language Models Against Split-Image Harmful Input Attacks","created":"2026-02-08","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":"2603.00565","title":"MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs","created":"2026-02-28","cited_by_count":1,"area":"mllm"},{"id":"2605.18915","title":"DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs","created":"2026-05-18","cited_by_count":1,"area":"mllm"},{"id":"2603.01784","title":"Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.09246","title":"Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models","created":"2026-03-10","cited_by_count":0,"area":"alignment"},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.09253","title":"Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2605.00699","title":"STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.05709","title":"Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2606.02111","title":"Jailbreaking Multimodal Large Language Models using Multi-Clip Video","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.07706","title":"MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models","created":"2026-06-05","cited_by_count":0,"area":"mllm"},{"id":"2606.24388","title":"PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models","created":"2026-06-23","cited_by_count":0,"area":"mllm"},{"id":"2607.10269","title":"Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices","created":"2026-07-11","cited_by_count":0,"area":"safety"},{"id":"2608.17234","title":"COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models","created":"2026-08-18","cited_by_count":0,"area":"mllm"},{"id":"2608.19737","title":"TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling","created":"2026-08-20","cited_by_count":0,"area":"mllm"},{"id":"2608.21100","title":"ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models","created":"2026-08-21","cited_by_count":0,"area":"mllm"},{"id":"2608.22312","title":"Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2609.22234","title":"Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.33833","title":"One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.07009","title":"Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks","created":"2026-10-04","cited_by_count":0,"area":"safety"},{"id":"2610.14094","title":"Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}