Yu-Hsuan Li Liang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Sound×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider cost and usability alongside success rates.
Highlighted terms show continued research focus across papers