Showing 21–32 of 32 results
/ Date/ Name
Sep 8, 2025Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?Mar 7, 2026Two Frames Matter: A Temporal Attack for Text-to-Video Model JailbreakingJan 12, 2026DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News DetectionSep 24, 2025Detoxifying Large Language Models via Autoregressive Reward Guided Representation EditingJul 29, 2025PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM JailbreakingMay 7, 2026SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent SafetyNov 25, 2024CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurityJan 21, 2025CogMorph: Cognitive Morphing Attacks for Text-to-Image ModelsJun 4, 2025PRJ: Perception-Retrieval-Judgement for Generated ImagesDec 19, 2025Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News DetectionApr 19, 2025Manipulating Multimodal Agents via Cross-Modal Prompt InjectionDec 24, 2025RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic