7 citations · 7 across the 4 of their papers we have counts for
4 papers
AID-Guard: Stateful Authorization for Delegated Agent Effects
Yingzhe Tong, Leyu Dai, Songhui Guo
Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and recovery evolve. A request may…
CE-based white-box adversarial attacks will not work using super-fitting
Youhuan Yang, Lei Sun, Leyu Dai +4
Deep neural networks are widely used in various fields because of their powerful performance. However, recent studies have shown that deep learning models are vulnerable to adversa…
Rethinking Classifier and Adversarial Attack
Youhuan Yang, Lei Sun, Leyu Dai +4
Various defense models have been proposed to resist adversarial attack algorithms, but existing adversarial robustness evaluation methods always overestimate the adversarial robust…
Patient similarity: methods and applications
Leyu Dai, He Zhu, Dianbo Liu
Patient similarity analysis is important in health care applications. It takes patient information such as their electronic medical records and genetic data as input and computes t…