2 papers
cs.AI2026
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
Tianshi Wang, Jingsong Wang, Fengling Li +3
Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not establish what a risk score…
cs.CR2026
MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities
Tianshi Wang, Jingsong Wang, Yafei Huang +3
Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet how different factors shape their jailbreak vulnerabilities remains poorly unders…