Yuan Hong
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, vulnerable code structures.
This paper investigates the vulnerability of Graph Neural Networks (GNNs) protected by Local Differential Privacy (LDP) to adversarial attacks, analyzing the interplay between privacy guarantees and adversarial robustness.
This paper introduces TC-UMIA, a novel tri-class membership inference attack, demonstrating that machine unlearning can leak privacy risks to the retained data set, and evaluates defense mechanisms to mitigate this risk.
The paper proposes W-IR, a novel watermarking framework that simultaneously achieves high certified robustness against adversarial attacks and effectively mitigates identity leakage in watermarked images.
Papers
"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
Xinyu Zhang, Ziping Dong, Qingyu Liu, Yuan Hong +2 more
The paper proposes W-IR, a novel watermarking framework that simultaneously achieves high certified robustness against adversarial attacks and effectively mitigates identity leakage in watermarked ima…