Xingjun Ma

On the Convergence and Robustness of Adversarial Training

2021 · arXiv (Cornell University)

Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques, adversarial training with Projected Gradient Decent (PGD) is amongst the …

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

2018 · Own your potential (DEAKIN)

© Learning Representations, ICLR 2018 - Conference Track Proceedings.All right reserved. Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to …

Backdoor Attacks on Time Series: A Generative Approach

2022 · arXiv (Cornell University)

Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. …

White-box Multimodal Jailbreaks Against Large Vision-Language Models

2024

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness through unimodal adversarial attacks …

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks

2025

As deep learning models are increasingly deployed in safety-critical applications, evaluating their vulnerabilities to adversarial perturbations is essential for ensuring their reliability and trustworthiness. Over the past decade, a large number of white-box adversarial robustness …