Xiaojin Zhang

No Free Lunch Theorem for Security and Utility in Federated Learning

2022 · ACM Transactions on Intelligent Systems and Technology

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive training data …

Trading Off Privacy, Utility and Efficiency in Federated Learning

2022 · arXiv (Cornell University)

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving \textit{privacy} …

Bridging Privacy and Robustness for Trustworthy Machine Learning

2024 · arXiv (Cornell University)

The widespread adoption of machine learning necessitates robust privacy protection alongside algorithmic resilience. While Local Differential Privacy (LDP) provides foundational guarantees, sophisticated adversaries with prior knowledge demand more nuanced Bayesian privacy notions, such as Maximum …

VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related …