{"total":117,"rows":[{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183,"area":"mllm"},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144,"area":"mllm"},{"id":"2411.10414","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","created":"2024-11-15","cited_by_count":129,"area":"mllm"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117,"area":"mllm"},{"id":"2312.03777","title":"On the Robustness of Large Multimodal Models Against Image Adversarial Attacks","created":"2023-12-06","cited_by_count":92,"area":"mllm"},{"id":"2402.14683","title":"Visual Hallucinations of Multi-modal Large Language Models","created":"2024-02-22","cited_by_count":68,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2402.06659","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","created":"2024-02-05","cited_by_count":50,"area":"mllm"},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48,"area":"mllm"},{"id":"2410.05346","title":"AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models","created":"2024-10-07","cited_by_count":46,"area":"mllm"},{"id":"2403.09766","title":"An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models","created":"2024-03-14","cited_by_count":45,"area":"mllm"},{"id":"2311.11261","title":"Adversarial Prompt Tuning for Vision-Language Models","created":"2023-11-19","cited_by_count":44,"area":"mllm"},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"id":"2403.14774","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","created":"2024-03-21","cited_by_count":39,"area":"mllm"},{"id":"2504.11195","title":"R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning","created":"2025-04-15","cited_by_count":33,"area":"mllm"},{"id":"2404.19287","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","created":"2024-04-30","cited_by_count":28,"area":"mllm"},{"id":"2502.17832","title":"MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks","created":"2025-02-25","cited_by_count":24,"area":"mllm"},{"id":"2410.21802","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models","created":"2024-10-29","cited_by_count":23,"area":"mllm"},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2411.13136","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","created":"2024-11-20","cited_by_count":23,"area":"mllm"},{"id":"2312.01886","title":"InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models","created":"2023-12-04","cited_by_count":21,"area":"mllm"},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2406.09250","title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","created":"2024-06-13","cited_by_count":19,"area":"mllm"},{"id":"2402.10340","title":"On the Vulnerability of LLM/VLM-Controlled Robotics","created":"2024-02-15","cited_by_count":15,"area":"mllm"},{"id":"2405.04403","title":"Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks","created":"2024-05-07","cited_by_count":15,"area":"mllm"},{"id":"2510.24038","title":"Enhancing CLIP Robustness via Cross-Modality Alignment","created":"2025-10-28","cited_by_count":15,"area":"mllm"},{"id":"2312.04960","title":"MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness","created":"2023-12-08","cited_by_count":12,"area":"mllm"},{"id":"2505.19911","title":"Attention! Your Vision Language Model Could Be Maliciously Manipulated","created":"2025-05-26","cited_by_count":12,"area":"mllm"},{"id":"2407.07392","title":"Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems","created":"2024-07-10","cited_by_count":11,"area":"mllm"},{"id":"2501.09446","title":"Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness","created":"2025-01-16","cited_by_count":10,"area":"mllm"},{"id":"2505.01050","title":"Transferable Adversarial Attacks on Black-Box Vision-Language Models","created":"2025-05-02","cited_by_count":10,"area":"mllm"},{"id":"2602.12158","title":"SafeNeuron: Neuron-Level Safety Alignment for Large Language Models","created":"2026-02-12","cited_by_count":10,"area":"mllm"},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2407.20657","title":"Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks","created":"2024-07-30","cited_by_count":9,"area":"mllm"},{"id":"2502.01576","title":"Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models","created":"2025-02-03","cited_by_count":9,"area":"mllm"},{"id":"2505.15130","title":"Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models","created":"2025-05-21","cited_by_count":9,"area":"mllm"},{"id":"2511.07049","title":"From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge","created":"2025-11-10","cited_by_count":9,"area":"mllm"},{"id":"2504.01735","title":"AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2505.17440","title":"VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models","created":"2025-05-23","cited_by_count":8,"area":"mllm"},{"id":"2408.13461","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","created":"2024-08-24","cited_by_count":7,"area":"mllm"},{"id":"2504.11038","title":"QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models","created":"2025-04-15","cited_by_count":7,"area":"mllm"},{"id":"2407.09050","title":"Refusing Safe Prompts for Multi-modal Large Language Models","created":"2024-07-12","cited_by_count":6,"area":"mllm"},{"id":"2502.07987","title":"Universal Adversarial Attack on Aligned Multimodal LLMs","created":"2025-02-11","cited_by_count":6,"area":"mllm"},{"id":"2503.12874","title":"Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models","created":"2025-03-17","cited_by_count":6,"area":"mllm"},{"id":"2503.22720","title":"Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models","created":"2025-03-25","cited_by_count":6,"area":"mllm"},{"id":"2502.01530","title":"The in-context inductive biases of vision-language models differ across modalities","created":"2025-02-03","cited_by_count":5,"area":"mllm"},{"id":"2510.09008","title":"On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models","created":"2025-10-10","cited_by_count":5,"area":"mllm"},{"id":"2512.03508","title":"Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation","created":"2025-12-03","cited_by_count":5,"area":"mllm"},{"id":"2311.09024","title":"Fast Certification of Vision-Language Models Using Incremental Randomized Smoothing","created":"2023-11-15","cited_by_count":4,"area":"mllm"},{"id":"2406.13294","title":"Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens","created":"2024-06-19","cited_by_count":4,"area":"mllm"},{"id":"2504.03714","title":"Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2507.08982","title":"VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models","created":"2025-07-11","cited_by_count":4,"area":"mllm"},{"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":"2405.14612","title":"Explaining Multi-modal Large Language Models by Analyzing their Vision Perception","created":"2024-05-23","cited_by_count":3,"area":"mllm"},{"id":"2504.01308","title":"Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks","created":"2025-04-02","cited_by_count":3,"area":"mllm"},{"id":"2504.16936","title":"Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness","created":"2025-04-03","cited_by_count":3,"area":"mllm"},{"id":"2606.00828","title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2412.10353","title":"Robust image classification with multi-modal large language models","created":"2024-12-13","cited_by_count":2,"area":"mllm"},{"id":"2502.08079","title":"MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models","created":"2025-02-12","cited_by_count":2,"area":"mllm"},{"id":"2504.16433","title":"FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing","created":"2025-04-23","cited_by_count":2,"area":"mllm"},{"id":"2505.02971","title":"Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation","created":"2025-05-05","cited_by_count":2,"area":"mllm"},{"id":"2507.22398","title":"On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations","created":"2025-07-30","cited_by_count":2,"area":"mllm"},{"id":"2510.26830","title":"SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation","created":"2025-10-29","cited_by_count":2,"area":"mllm"},{"id":"2512.16523","title":"TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models","created":"2025-12-18","cited_by_count":2,"area":"mllm"},{"id":"2602.15927","title":"Visual Memory Injection Attacks for Multi-Turn Conversations","created":"2026-02-17","cited_by_count":2,"area":"mllm"},{"id":"2502.19672","title":"Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack","created":"2025-02-27","cited_by_count":1,"area":"mllm"},{"id":"2506.00534","title":"The Security Threat of Compressed Projectors in Large Vision-Language Models","created":"2025-05-31","cited_by_count":1,"area":"mllm"},{"id":"2506.11472","title":"Toward Inherently Robust VLMs Against Visual Perception Attacks","created":"2025-06-13","cited_by_count":1,"area":"mllm"},{"id":"2506.12336","title":"Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding","created":"2025-06-14","cited_by_count":1,"area":"mllm"},{"id":"2509.06992","title":"FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models","created":"2025-09-03","cited_by_count":1,"area":"mllm"},{"id":"2509.16088","title":"Randomized Smoothing Meets Vision-Language Models","created":"2025-09-19","cited_by_count":1,"area":"mllm"},{"id":"2510.09849","title":"Text Prompt Injection of Vision Language Models","created":"2025-10-10","cited_by_count":1,"area":"mllm"},{"id":"2512.21815","title":"High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models","created":"2025-12-26","cited_by_count":1,"area":"mllm"},{"id":"2602.15278","title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","created":"2026-02-17","cited_by_count":1,"area":"mllm"},{"id":"2603.26984","title":"A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models","created":"2026-03-27","cited_by_count":1,"area":"mllm"},{"id":"2603.29410","title":"AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models","created":"2026-03-31","cited_by_count":1,"area":"mllm"},{"id":"2604.09024","title":"Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection","created":"2026-04-10","cited_by_count":1,"area":"mllm"},{"id":"2604.11576","title":"Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.18867","title":"Hierarchically Robust Zero-shot Vision-language Models","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2605.16651","title":"Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations","created":"2026-05-15","cited_by_count":1,"area":"mllm"},{"id":"2606.06186","title":"Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2606.06938","title":"When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness","created":"2026-06-05","cited_by_count":1,"area":"mllm"},{"id":"2608.18938","title":"Breaking the weakest link to evade vision language models","created":"2026-08-19","cited_by_count":1,"area":"mllm"},{"id":"2402.03627","title":"Partially Recentralization Softmax Loss for Vision-Language Models Robustness","created":"2024-02-06","cited_by_count":0,"area":"mllm"},{"id":"2505.17509","title":"MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language Models","created":"2025-05-23","cited_by_count":0,"area":"mllm"},{"id":"2506.05429","title":"Coordinated Robustness Evaluation Framework for Vision-Language Models","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2506.22982","title":"Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models","created":"2025-06-28","cited_by_count":0,"area":"mllm"},{"id":"2509.19858","title":"Benchmarking Gaslighting Attacks Against Speech Large Language Models","created":"2025-09-24","cited_by_count":0,"area":"mllm"},{"id":"2510.02913","title":"Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting","created":"2025-10-03","cited_by_count":0,"area":"mllm"},{"id":"2511.20002","title":"Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation","created":"2025-11-25","cited_by_count":0,"area":"mllm"},{"id":"2601.10313","title":"Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models","created":"2026-01-15","cited_by_count":0,"area":"mllm"},{"id":"2601.12865","title":"Proxy Robustness in Vision Language Models is Effortlessly Transferable","created":"2026-01-19","cited_by_count":0,"area":"mllm"},{"id":"2601.21220","title":"LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models","created":"2026-01-29","cited_by_count":0,"area":"mllm"},{"id":"2603.00172","title":"Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation","created":"2026-02-26","cited_by_count":0,"area":"mllm"},{"id":"2603.15259","title":"Directional Embedding Smoothing for Robust Vision Language Models","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2603.18598","title":"Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness","created":"2026-03-19","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}