{"total":120,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"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":"2411.18275","title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","created":"2024-11-27","cited_by_count":36,"area":"lr"},{"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":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"area":"agents"},{"id":"2403.09346","title":"B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions","created":"2024-03-14","cited_by_count":26,"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":"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":"2503.03613","title":"CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP","created":"2025-03-05","cited_by_count":23,"area":null},{"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":"2410.00296","title":"VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild","created":"2024-10-01","cited_by_count":18,"area":"mllm"},{"id":"2503.13962","title":"Survey of Adversarial Robustness in Multimodal Large Language Models","created":"2025-03-18","cited_by_count":16,"area":"mllm"},{"id":"2409.07353","title":"Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks","created":"2024-09-11","cited_by_count":15,"area":"mllm"},{"id":"2506.02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","created":"2025-06-03","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":"2512.22894","title":"DECEPTICON: How Dark Patterns Manipulate Web Agents","created":"2025-12-28","cited_by_count":15,"area":"agents"},{"id":"2502.18290","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","created":"2025-02-25","cited_by_count":14,"area":"mllm"},{"id":"2503.09837","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","created":"2025-03-12","cited_by_count":13,"area":"mllm"},{"id":"2407.14971","title":"Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models","created":"2024-07-20","cited_by_count":12,"area":"mllm"},{"id":"2503.04833","title":"E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models","created":"2025-03-05","cited_by_count":12,"area":"mllm"},{"id":"2503.10809","title":"MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents","created":"2025-03-13","cited_by_count":12,"area":"agents"},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2511.17448","title":"MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models","created":"2025-11-21","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":"2502.11725","title":"Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9,"area":"mllm"},{"id":"2412.14097","title":"Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts","created":"2024-12-18","cited_by_count":9,"area":null},{"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":"2503.01887","title":"When Continue Learning Meets Multimodal Large Language Model: A Survey","created":"2025-02-27","cited_by_count":9,"area":"mllm"},{"id":"2511.20223","title":"V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs","created":"2025-11-25","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":"2410.01574","title":"Adversarial Robustness of AI-Generated Image Detectors in the Real World","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2411.15244","title":"Adversarial Prompt Distillation for Vision-Language Models","created":"2024-11-22","cited_by_count":6,"area":"mllm"},{"id":"2503.18695","title":"OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2407.11121","title":"Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques","created":"2024-07-15","cited_by_count":5,"area":"mllm"},{"id":"2412.19920","title":"Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models","created":"2024-12-27","cited_by_count":5,"area":null},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2508.13739","title":"Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector","created":"2025-08-19","cited_by_count":5,"area":"mllm"},{"id":"2509.19994","title":"Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2603.05235","title":"Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2603.29080","title":"Is the Modality Gap a Bug or a Feature? A Robustness Perspective","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2502.07225","title":"CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models","created":"2025-02-11","cited_by_count":4,"area":"diffusion"},{"id":"2508.00756","title":"LeakyCLIP: Extracting Training Data from CLIP","created":"2025-08-01","cited_by_count":4,"area":"diffusion"},{"id":"2508.15370","title":"Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation","created":"2025-08-21","cited_by_count":4,"area":"mllm"},{"id":"2511.00446","title":"ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training","created":"2025-11-01","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":"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":"2505.24208","title":"Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap","created":"2025-05-30","cited_by_count":3,"area":"mllm"},{"id":"2508.10637","title":"Processing and acquisition traces in visual encoders: What does CLIP know about your camera?","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2602.19418","title":"PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention","created":"2026-02-23","cited_by_count":3,"area":"mllm"},{"id":"2605.08896","title":"FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2504.05838","title":"Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2505.06580","title":"TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2506.03933","title":"Diffusion-based Cumulative Adversarial Purification for Vision Language Models","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2507.00670","title":"Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2508.20760","title":"Occlusion Robustness of CLIP for Military Vehicle Classification","created":"2025-08-28","cited_by_count":2,"area":"mllm"},{"id":"2510.21532","title":"FrameShield: Adversarially Robust Video Anomaly Detection","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2601.19210","title":"Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2405.18770","title":"Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships","created":"2024-05-29","cited_by_count":1,"area":"mllm"},{"id":"2411.00898","title":"Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models","created":"2024-11-01","cited_by_count":1,"area":"lr"},{"id":"2503.11195","title":"Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Models","created":"2025-03-14","cited_by_count":1,"area":"safety"},{"id":"2505.22604","title":"Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2511.14106","title":"Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT","created":"2025-11-18","cited_by_count":1,"area":"lr"},{"id":"2511.17362","title":"ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2512.12997","title":"Calibrating Uncertainty for Zero-Shot Adversarial CLIP","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2603.08800","title":"Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM","created":"2026-03-09","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":"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":"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":"2606.18839","title":"Semantic Robustness Certification for Vision-Language Models","created":"2026-06-17","cited_by_count":1,"area":"mllm"},{"id":"2607.03165","title":"Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2405.07969","title":"Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2410.13010","title":"Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2505.11895","title":"Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2505.14204","title":"Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment","created":"2025-05-20","cited_by_count":0,"area":null},{"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":"2505.18884","title":"LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2509.14383","title":"RLBind: Adversarial-Invariant Cross-Modal Alignment for Unified Robust Embeddings","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.15435","title":"ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models","created":"2025-09-18","cited_by_count":0,"area":"lr"},{"id":"2509.16163","title":"Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks","created":"2025-09-19","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":"2510.06790","title":"Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2511.21893","title":"Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.07222","title":"Pay Less Attention to Function Words for Free Robustness of Vision-Language Models","created":"2025-12-08","cited_by_count":0,"area":"mllm"},{"id":"2601.08355","title":"Semantic Misalignment in Vision-Language Models under Perceptual Degradation","created":"2026-01-13","cited_by_count":0,"area":"mllm"},{"id":"2601.16200","title":"Feature-Space Smoothing: Certified Robustness of Deep Representations","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.13293","title":"NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Driving","created":"2026-02-09","cited_by_count":0,"area":"mllm"},{"id":"2602.18252","title":"On the Adversarial Robustness of Discrete Image Tokenizers","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2602.22013","title":"RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations","created":"2026-02-25","cited_by_count":0,"area":"mllm"},{"id":"2603.12799","title":"What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models","created":"2026-03-13","cited_by_count":0,"area":"mllm"},{"id":"2603.18545","title":"CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models","created":"2026-03-19","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"},{"id":"2603.27139","title":"The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models","created":"2026-03-28","cited_by_count":0,"area":"mllm"},{"id":"2604.01010","title":"PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2604.04473","title":"Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks","created":"2026-04-06","cited_by_count":0,"area":"mllm"},{"id":"2605.01449","title":"VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models","created":"2026-05-02","cited_by_count":0,"area":"mllm"},{"id":"2605.07273","title":"From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG","created":"2026-05-08","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}