Choongwon Kang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Jailbreaking Multimodal Large Language Models using Multi-Clip Video
The paper introduces Multi-Clip Video (MCV) SafetyBench, a dataset demonstrating that the vulnerability of Multimodal Large Language Models (MLLMs) to jailbreaking increases with the diversity and number of clips in video inputs.
Highlighted terms show continued research focus across papers