Zihan Zhang
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper introduces the Relay Tampering Attack (RTA), demonstrating that malicious third-party relays can undermine the security of LLM agents by modifying responses post-alignment, even if the LLM itself is perfectly aligned.
The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realistic, open-ended scenarios.
The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realistic, open-ended scenarios.
This paper proposes X$^3$-OPD, a framework for transferring reasoning capabilities from text-based models to audio-language models using on-policy distillation.
This paper introduces AffectDF, a comprehensive benchmark for emotionally expressive speech deepfakes, revealing severe robustness degradation of state-of-the-art SDD systems.
Papers
AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks
This paper introduces AffectDF, a comprehensive benchmark for emotionally expressive speech deepfakes, revealing severe robustness degradation of state-of-the-art SDD systems.