{"total":103,"rows":[{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2311.16119","title":"Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition","created":"2023-10-24","cited_by_count":68,"area":"safety"},{"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":"2311.11261","title":"Adversarial Prompt Tuning for Vision-Language Models","created":"2023-11-19","cited_by_count":44,"area":"mllm"},{"id":"2407.20242","title":"BadRobot: Jailbreaking Embodied LLM Agents in the Physical World","created":"2024-07-16","cited_by_count":43,"area":"agents"},{"id":"2312.04913","title":"SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation","created":"2023-12-08","cited_by_count":39,"area":"mllm"},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39,"area":"safety"},{"id":"2312.04403","title":"OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization","created":"2023-12-07","cited_by_count":37,"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":"2502.10794","title":"Distraction is All You Need for Multimodal Large Language Model Jailbreaking","created":"2025-02-15","cited_by_count":36,"area":"mllm"},{"id":"2409.17874","title":"DarkSAM: Fooling Segment Anything Model to Segment Nothing","created":"2024-09-26","cited_by_count":32,"area":null},{"id":"2405.05524","title":"Universal Adversarial Perturbations for Vision-Language Pre-trained Models","created":"2024-05-09","cited_by_count":31,"area":"mllm"},{"id":"2408.01428","title":"Transferable Adversarial Facial Images for Privacy Protection","created":"2024-07-18","cited_by_count":27,"area":null},{"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":"2509.16645","title":"ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents","created":"2025-09-20","cited_by_count":23,"area":"lr"},{"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":"2403.10801","title":"Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples","created":"2024-03-16","cited_by_count":21,"area":null},{"id":"2410.20197","title":"Transferable Adversarial Attacks on SAM and Its Downstream Models","created":"2024-10-26","cited_by_count":21,"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":"2404.05264","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","created":"2024-04-08","cited_by_count":19,"area":"mllm"},{"id":"2412.16955","title":"NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors","created":"2024-12-22","cited_by_count":17,"area":null},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15,"area":null},{"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":"2412.16651","title":"PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation","created":"2024-12-21","cited_by_count":14,"area":null},{"id":"2503.15293","title":"Test-Time Backdoor Detection for Object Detection Models","created":"2025-03-19","cited_by_count":14,"area":null},{"id":"2412.16958","title":"Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature","created":"2024-12-22","cited_by_count":13,"area":null},{"id":"2511.21192","title":"When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models","created":"2025-11-26","cited_by_count":13,"area":"vla"},{"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":"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":"2510.24195","title":"Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2","created":"2025-10-28","cited_by_count":11,"area":null},{"id":"2409.15968","title":"Adversarial Backdoor Defense in CLIP","created":"2024-09-24","cited_by_count":10,"area":"safety"},{"id":"2406.15093","title":"ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification","created":"2024-06-21","cited_by_count":9,"area":null},{"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":"2401.08903","title":"Rethinking Impersonation and Dodging Attacks on Face Recognition Systems","created":"2024-01-17","cited_by_count":8,"area":null},{"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":"2506.15115","title":"Towards Reliable Forgetting: A Survey on Machine Unlearning Verification","created":"2025-06-18","cited_by_count":8,"area":"safety"},{"id":"2510.08922","title":"SegTrans: Transferable Adversarial Examples for Segmentation Models","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2510.08094","title":"DarkHash: A Data-Free Backdoor Attack Against Deep Hashing","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2504.21646","title":"Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2505.23518","title":"TRAP: Targeted Redirecting of Agentic Preferences","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2602.03284","title":"Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2310.12431","title":"SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2312.17431","title":"MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2405.16940","title":"Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2407.17797","title":"A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models","created":"2024-07-25","cited_by_count":4,"area":"mllm"},{"id":"2411.15555","title":"Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation","created":"2024-11-23","cited_by_count":4,"area":null},{"id":"2503.12793","title":"Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"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":"2401.14074","title":"ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation","created":"2024-01-25","cited_by_count":3,"area":null},{"id":"2407.18658","title":"Adversarial Robustification via Text-to-Image Diffusion Models","created":"2024-07-26","cited_by_count":3,"area":"diffusion"},{"id":"2507.00817","title":"CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs","created":"2025-07-01","cited_by_count":3,"area":"lr"},{"id":"2508.20040","title":"Model Science: getting serious about verification, explanation and control of AI systems","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2601.03594","title":"Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2601.14950","title":"Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2607.12624","title":"PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis","created":"2026-07-14","cited_by_count":3,"area":"agents"},{"id":"2403.00376","title":"Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model","created":"2024-03-01","cited_by_count":2,"area":"mllm"},{"id":"2404.11357","title":"Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2408.02980","title":"Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models","created":"2024-08-06","cited_by_count":2,"area":"mllm"},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2504.21044","title":"AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection","created":"2025-04-28","cited_by_count":2,"area":"safety"},{"id":"2505.23266","title":"Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2507.01042","title":"Can Argus Judge Them All? Comparing VLMs Across Domains","created":"2025-06-23","cited_by_count":2,"area":"mllm"},{"id":"2508.17680","title":"Robustness Feature Adapter for Efficient Adversarial Training","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.23917","title":"Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives","created":"2025-09-28","cited_by_count":2,"area":"mllm"},{"id":"2512.11336","title":"UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models","created":"2025-12-12","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":"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":"2604.12371","title":"Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2401.14031","title":"Sparse and Transferable Universal Singular Vectors Attack","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2408.01705","title":"Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers","created":"2024-08-03","cited_by_count":1,"area":null},{"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":"2501.18006","title":"Topological Signatures of Adversaries in Multimodal Alignments","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2504.11509","title":"PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage","created":"2025-04-15","cited_by_count":1,"area":"mllm"},{"id":"2506.12411","title":"InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning","created":"2025-06-14","cited_by_count":1,"area":"safety"},{"id":"2510.08067","title":"Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2512.16126","title":"Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure","created":"2025-12-18","cited_by_count":1,"area":"safety"},{"id":"2603.03665","title":"Machine Pareidolia: Protecting Facial Image with Emotional Editing","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.23105","title":"Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2407.18251","title":"Sparse vs Contiguous Adversarial Pixel Perturbations in Multimodal Models: An Empirical Analysis","created":"2024-07-25","cited_by_count":0,"area":null},{"id":"2409.06726","title":"Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models","created":"2024-08-27","cited_by_count":0,"area":"mllm"},{"id":"2505.15265","title":"Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.05402","title":"Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.21084","title":"Vision Transformers: the threat of realistic adversarial patches","created":"2025-09-25","cited_by_count":0,"area":null},{"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":"2601.10313","title":"Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models","created":"2026-01-15","cited_by_count":0,"area":"mllm"},{"id":"2601.21220","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":"2603.12799","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":"2604.25102","title":"One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations","created":"2026-04-28","cited_by_count":0,"area":"mllm"},{"id":"2605.17577","title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","created":"2026-05-17","cited_by_count":0,"area":"mllm"},{"id":"2605.18868","title":"DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.10371","title":"Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies","created":"2026-06-09","cited_by_count":0,"area":"diffusion"},{"id":"2606.19736","title":"VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.06485","title":"AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.14737","title":"GeoDetect: Geometric Adversarial Detection for VLPs","created":"2026-07-16","cited_by_count":0,"area":"mllm"},{"id":"2607.14974","title":"On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline","created":"2026-07-16","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}],"next_cursor":"100"}