Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models Paper • 2602.01025 • Published 25 days ago
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs Paper • 2601.21233 • Published 28 days ago
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models Paper • 2511.18921 • Published Nov 24, 2025
AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds Paper • 2509.04345 • Published Sep 4, 2025
T2UE: Generating Unlearnable Examples from Text Descriptions Paper • 2508.03091 • Published Aug 5, 2025
CURVALID: Geometrically-guided Adversarial Prompt Detection Paper • 2503.03502 • Published Mar 5, 2025