"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Documenti analoghi

• Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
  di: Cheng, Hao, et al.
  Pubblicazione: (2025)
• AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
  di: Chen, Guangke, et al.
  Pubblicazione: (2025)
• TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining
  di: Primus, Paul, et al.
  Pubblicazione: (2025)
• Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs
  di: Sinha, Anshuman, et al.
  Pubblicazione: (2024)
• Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
  di: Kong, Zhifeng, et al.
  Pubblicazione: (2024)