Ye Lu
3 indexed papers
Research Timeline
The paper proposes a novel adversarial defense approach, TopFeaRe, by modeling graph adversarial attacks using complex dynamic system theory to locate the graph's critical state of resilience.
This paper proposes DPIFrame, a dual parallelizable framework for accelerating Click-through rate (CTR) model inference on GPU, achieving state-of-the-art inference performance with significant speedups.
This paper introduces Audio BERT (AuB) and SpInv, methods for recovering embeddings from speech tokens and performing speaker inversion attacks using only three seconds of frontend output.
Papers
Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models
Ye Lu, Yihan Yan, Zhaoyang Zhang, Zhitao Ou +3 more
This paper introduces Audio BERT (AuB) and SpInv, methods for recovering embeddings from speech tokens and performing speaker inversion attacks using only three seconds of frontend output.