{"total":31,"rows":[{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2502.13175","title":"Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks","created":"2025-02-18","cited_by_count":34,"area":null},{"id":"2504.01081","title":"ShieldGemma 2: Robust and Tractable Image Content Moderation","created":"2025-04-01","cited_by_count":28,"area":null},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14,"area":null},{"id":"2503.11519","title":"Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models","created":"2025-03-14","cited_by_count":14,"area":null},{"id":"2510.00181","title":"CHAI: Command Hijacking against embodied AI","created":"2025-09-30","cited_by_count":11,"area":null},{"id":"2507.06256","title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2509.26636","title":"AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2412.07334","title":"Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2505.04673","title":"REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM","created":"2025-05-07","cited_by_count":5,"area":null},{"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":"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":"2410.13114","title":"Sound Check: Auditing Audio Datasets","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2505.04488","title":"\"I Can See Forever!\": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments","created":"2025-05-07","cited_by_count":3,"area":null},{"id":"2509.23783","title":"Falcon: A Cross-Modal Evaluation Dataset for Comprehensive Safety Perception","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2603.27332","title":"Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2605.13213","title":"Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.15118","title":"Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.03348","title":"SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.25592","title":"VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2511.03699","title":"Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language Models","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2607.11560","title":"Technical Report on the CVPR 2026@AdvML Workshop Challenge","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.03139","title":"Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.05843","title":"SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation","created":"2026-09-05","cited_by_count":0,"area":null},{"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":"2609.38802","title":"Uncovering Uncontrolled Repetition through Residual Stream Dynamics","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.13252","title":"Vision Transformers Learn Word Meaning from Images Alone","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15728","title":"Visually Legible but Adversarial: Watermark-Constrained Attacks on End-to-End VLMs for Document Understanding","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}