{"total":31,"rows":[{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"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":"2411.05056","title":"Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models","created":"2024-11-07","cited_by_count":4,"area":"mllm"},{"id":"2509.25178","title":"GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs","created":"2025-09-29","cited_by_count":4,"area":"mllm"},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2602.01025","title":"Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models","created":"2026-02-01","cited_by_count":4,"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":"2601.22737","title":"Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models","created":"2026-01-30","cited_by_count":2,"area":"mllm"},{"id":"2605.08560","title":"ZAYA1-VL-8B Technical Report","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"id":"2605.21541","title":"Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2607.00174","title":"Steal the Patch Size: Adversarially Manipulate Vision-Language Models","created":"2026-06-30","cited_by_count":2,"area":"mllm"},{"id":"2601.23179","title":"Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2605.07447","title":"Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2605.09902","title":"Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment","created":"2026-05-11","cited_by_count":1,"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":"2602.04356","title":"Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models","created":"2026-02-04","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":"2603.29418","title":"Covert Visual Prompt Injection against Commercial Multimodal Large Language Models","created":"2026-03-31","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":"2604.03117","title":"Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models","created":"2026-04-03","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":"2606.00390","title":"Zamba2-VL Technical Report","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.23892","title":"REALM: A Unified Red-Teaming Benchmark for Physical-World VLMs","created":"2026-06-22","cited_by_count":0,"area":"mllm"},{"id":"2608.07535","title":"Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2609.35002","title":"Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.36648","title":"VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-training","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.38298","title":"It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $ε\\leq 4/255$","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.39134","title":"Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.06977","title":"Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs","created":"2026-10-04","cited_by_count":0,"area":"mllm"},{"id":"2610.11938","title":"Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders","created":"2026-10-08","cited_by_count":0,"area":"mllm"},{"id":"2610.20055","title":"GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}