Dang Nguyen

I am a Ph.D. student in Computer Science at the University of Maryland, College Park, advised by Professor Tianyi Zhou. I received my B.E. degree at the Ho Chi Minh City University of Technology. Before joining UMD, I worked as an AI Research Resident at VinAI Research with Professor Luu Anh Tuan.

News

Dec 9, 2023	One paper accepted at AAAI 2024.
Oct 6, 2022	One paper accepted at EMNLP 2022.

Publications

AAAI

COMBAT: Alternated Training for Effective Clean-Label Backdoor Attacks

Tran Huynh, Dang Nguyen, Tung Pham, and Anh Tran

The 38th Annual AAAI Conference on Artificial Intelligence. 2024

Abs PDF

Backdoor attacks pose a critical concern to the practice of using third-party data for AI development. The data can be poisoned to make a trained model misbehave when a predefined trigger pattern appears, granting the attackers illegal benefits. While most proposed backdoor attacks are dirty-label, clean-label attacks are more desirable by keeping data labels unchanged to dodge human inspection. However, designing a working clean-label attack is a challenging task, and existing clean-label attacks show underwhelming performance. In this paper, we propose a novel mechanism to develop clean-label attacks with outstanding attack performance. The key component is a trigger pattern generator, which is trained together with a surrogate model in an alternating manner. Our proposed mechanism is flexible and customizable, allowing different backdoor trigger types and behaviors for either single or multiple target labels. Our backdoor attacks can reach near-perfect attack success rates and bypass all state-of-the-art backdoor defenses, as illustrated via comprehensive experiments on standard benchmark datasets.
EMNLP

Textual Manifold-based Defense against Natural Language Adversarial Examples

Dang Nguyen, and Luu Anh Tuan

The 2022 Conference on Empirical Methods in Natural Language Processing. 2022

Abs PDF Code

Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold conjecture has inspired a novel line of defenses against adversarial attacks on images. In this study, we find a similar phenomenon occurs in the contextualized embedding space induced by pretrained language models, in which adversarial texts tend to have their embeddings diverge from the manifold of natural ones. Based on this finding, we propose Textual Manifold-based Defense (TMD), a defense mechanism that projects text embeddings onto an approximated embedding manifold before classification. It reduces the complexity of potential adversarial examples, which ultimately enhances the robustness of the protected model. Through extensive experiments, our method consistently and significantly outperforms previous defenses under various attack settings without trading off clean accuracy. To the best of our knowledge, this is the first NLP defense that leverages the manifold structure against adversarial attacks.