HearSay Benchmark: Do Audio LLMs Leak What They Hear?

Documenti analoghi

• ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
  di: Luo, Kaiwen, et al.
  Pubblicazione: (2026)
• Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
  di: Yu, Miao, et al.
  Pubblicazione: (2025)
• Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
  di: Lin, Liang, et al.
  Pubblicazione: (2025)
• SafeSeek: Universal Attribution of Safety Circuits in Language Models
  di: Yu, Miao, et al.
  Pubblicazione: (2026)
• MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
  di: Zhou, Zhenhong, et al.
  Pubblicazione: (2026)