Kun He

Fast Gradient Projection Method for Text Adversary Generation and Adversarial Training

2020 · arXiv (Cornell University)

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be …

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks

2022 · arXiv (Cornell University)

Deep neural networks have shown to be very vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to benign inputs. After achieving impressive attack success rates in the white-box setting, more focus is shifted to …

Fast Adversarial Training against Textual Adversarial Attacks

2024 · arXiv (Cornell University)

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates used by attackers …

Fading-Invariant Adversarial Attacks on Neural Modulation Recognition

2025

Despite significant advances in Deep Neural Networks (DNNs) for Neural Modulation Recognition (NMR) in wireless communications, recent research highlights their vulnerability to adversarial attacks. However, in practical wireless communication scenarios, adversarial signals transmitted by attackers …

HT-Auth: Secure VR Headset Authentication via Subtle Head Tremors

2025 · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies

While Virtual Reality (VR) applications have gained popularity in recent years, efficiently identifying users on VR devices remains challenging. Current solutions, such as passwords and digital PINs, relying on handheld controllers or in-air hand gestures, …

MagLive: Robust Voice Liveness Detection on Smartphones Using Magnetic Pattern Changes

2026 · IEEE Transactions on Information Forensics and Security

Voice authentication has been widely used on smartphones. However, it remains vulnerable to spoofing attacks, where the attacker replays recorded voice samples from authentic humans using loudspeakers to bypass the voice authentication system. In this …