Jaechul Roh
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1Sound×1
Frequent co-authors
Research Timeline
2026
Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
This paper demonstrates that benign fine-tuning significantly degrades safety in Audio LLMs, showing that the vulnerability is distinct from text and vision modalities and is highly dependent on the model's architecture.
Highlighted terms show continued research focus across papers