Huan Zhang

RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In …

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

2020 · arXiv (Cornell University)

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversarial …

Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data

2020 · arXiv (Cornell University)

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer from the issue …

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

2020 · arXiv (Cornell University)

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense. …

Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks.

2021 · arXiv (Cornell University)

Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image models that can have different characteristics in quantitative evaluation, consequences …

Cement Quality Management and Analysis System Development

2022 · 2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC)

This paper provides a detailed description of the cement quality management and analysis system. The use of SQL database is more standardized to establish a unified platform for cement plant data, and the client system …

Medical Specialty Classification Based on Semiadversarial Data Augmentation

2023 · Computational Intelligence and Neuroscience

Rapidly increasing adoption of electronic health record (EHR) systems has caused automated medical specialty classification to become an important research field. Medical specialty classification not only improves EHR system retrieval efficiency and helps general practitioners …

AutoSpec: Automated Generation of Neural Network Specifications

2024 · arXiv (Cornell University)

The increasing adoption of neural networks in learning-augmented systems highlights the growing need for model safety and robustness, especially in safety-critical domains. While recent advances in neural network verification offer formal guarantees on worst-case behavior, …

Loom: A Deterministic Execution Framework Towards Nested Contract Transactions

2025

Smart contracts have expanded blockchain applications, but permissioned blockchain systems face severe through-put challenges, especially with the increasing complexity of nested contract transactions. These transactions, involving cross-contract interactions and deep call chains, intensify execution conflicts …