Xiyu Shi
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes an enhanced Wasserstein GAN with Gradient Penalty (SA-JS-WGAN-GP) incorporating Self-Attention and Jensen-Shannon Divergence to synthesize diverse network traffic data, significantly improving the detection of zero-day attacks in Intrusion Detection Systems (IDS).
The paper introduces GMA-SAWGAN-GP, a novel generative framework that significantly enhances Intrusion Detection System (IDS) performance by augmenting mixed-type network traffic data, especially improving generalization to unknown attacks.
The paper introduces a novel byte-level method to encode network flow records into fixed-size RGB images, significantly improving the performance of Intrusion Detection Systems (IDS) by allowing convolutional architectures to exploit spatial correlations.
KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to existing baselines.
Papers
Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages
Shuoming Zhang, Qiuchu Yu, Yangyu Zhang, Ruiyuan Xu +5 more
KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to exi…