Jianwei Li

Jianwei Li, Sheng Liu, Qi Lei

Language models trained via federated learning (FL) demonstrate impressive capabilities in handling complex tasks while protecting user privacy. Recent studies indicate that leveraging gradient information and prior knowledge can potentially reveal training samples within FL setting. However, these investigations have overlooked the potential privacy risks tied to the intrinsic architecture of the models. This paper presents a two-stage privacy attack strategy that targets the vulnerabilities in the architecture of contemporary language models, significantly enhancing attack performance by initially recovering certain feature directions as additional supervisory signals. Our comparative experiments demonstrate superior attack performance across various datasets and scenarios, highlighting the privacy leakage risk associated with the increasingly complex architectures of language models. We call for the community to recognize and address these potential privacy risks in designing large language models.

Wendong Gan, Haitao Chen, Yin Yan et al.

This paper presents the IQIYI voice conversion system (T24) for Voice Conversion 2020. In the competition, each target speaker has 70 sentences. We have built an end-to-end voice conversion system based on PPG. First, the ASR acoustic model calculates the BN feature, which represents the content-related information in the speech. Then the Mel feature is calculated through an improved prosody tacotron model. Finally, the Mel spectrum is converted to wav through an improved LPCNet. The evaluation results show that this system can achieve better voice conversion effects. In the case of using 16k rather than 24k sampling rate audio, the conversion result is relatively good in naturalness and similarity. Among them, our best results are in the similarity evaluation of the Task 2, the 2nd in the ASV-based objective evaluation and the 5th in the subjective evaluation.

Divesh Aggarwal, Jianwei Li, Phong Q. Nguyen et al.

We show how to generalize Gama and Nguyen's slide reduction algorithm [STOC '08] for solving the approximate Shortest Vector Problem over lattices (SVP). As a result, we show the fastest provably correct algorithm for $δ$-approximate SVP for all approximation factors $n^{1/2+\varepsilon} \leq δ\leq n^{O(1)}$. This is the range of approximation factors most relevant for cryptography.