4 papers
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
Wonjun Lee, Haon Park, Doehyeon Lee +2
Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While recent studies have explored vulnerabilit…
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
Junwoo Ha, Hyunjun Kim, Sangyoon Yu +4
We introduce a novel framework for consolidating multi-turn adversarial ``jailbreak'' prompts into single-turn queries, significantly reducing the manual overhead required for adve…
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
Wonjun Lee, Doehyeon Lee, Eugene Choi +5
Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation…
Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
Wonjun Lee, Bumsub Ham, Suhyun Kim
In vision transformers, position embedding (PE) plays a crucial role in capturing the order of tokens. However, in vision transformer structures, there is a limitation in the expre…