4 papers
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
Bo-Han Feng, Yu-Hsuan Li Liang, Chien-Feng Liu +2
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced thro…
FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
Zekang Zhang, Guangyu Gao, Youyun Tang +7
LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mo…
Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
Bo-Han Feng, Chien-Feng Liu, Yu-Hsuan Li Liang +9
Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, a…
ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
Yu-Xiang Luo, Yi-Cheng Lin, Ming-To Chuang +9
Despite extensive research on toxic speech detection in text, a critical gap remains in handling spoken Mandarin audio. The lack of annotated datasets that capture the unique proso…