Thuy Dung Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thuy Dung Nguyen has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Huy Hieu Pham
VinUniversity
2 shared publications - Kevin Leach
Vanderbilt University, Nashville, TN, USA
2 shared publications - Phi Le Nguyen
Hanoi University of Science and Technology
2 shared publications - Preston K. Robinette
Vanderbilt University
2 shared publications - Samuel Sasaki
Vanderbilt University
2 shared publications - Taylor Thomas Johnson
Vanderbilt University
2 shared publications
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 20-38
Indelible Backdoors: On the Limits of Post-training Defenses
- 10 September 2026
- Published by Springer Nature
- p. 20-38
Indelible Backdoors: On the Limits of Post-training Defenses
- 13 October 2025
- Published by Springer Nature
- p. 346-365
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
- 13 October 2025
- Published by Springer Nature
- p. 346-365
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 616-620
Enhancing Code LLM Training with Programmer Attention
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 616-620
Open AccessEnhancing Code LLM Training with Programmer Attention
- Open Access
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile watermarking for model integrity has been studied in classification models, image transformation/generation models have yet to be explored. We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks that takes advantage of properties inherent to image outputs. For example, manifesting watermarks as specific visual patterns, styles, or anomalies in the generated content when particular trigger inputs are used. Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks, outperforming baselines by 94%. We conduct additional experiments to analyze the security of this approach, the flexibility of the trigger and resulting watermark, and the sensitivity of the watermarking loss on performance. We also demonstrate the applicability of this approach on two different tasks (1 immediate task and 1 downstream task). This is the first work to consider fragile model watermarking for image transformation/generation networks.
Open AccessTrigger-Based Fragile Model Watermarking for Image Transformation Networks
In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile watermarking for model integrity has been studied in classification models, image transformation/generation models have yet to be explored. We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks that takes advantage of properties inherent to image outputs. For example, manifesting watermarks as specific visual patterns, styles, or anomalies in the generated content when particular trigger inputs are used. Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks, outperforming baselines by 94%. We conduct additional experiments to analyze the security of this approach, the flexibility of the trigger and resulting watermark, and the sensitivity of the watermarking loss on performance. We also demonstrate the applicability of this approach on two different tasks (1 immediate task and 1 downstream task). This is the first work to consider fragile model watermarking for image transformation/generation networks.
- 9 December 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 128
GAMMA: A universal model for calibrating sensory data of multiple low-cost air monitoring devices
- 9 December 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 128
GAMMA: A universal model for calibrating sensory data of multiple low-cost air monitoring devices
- Top Cited Papers
- 5 October 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 127
Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions
- 5 October 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 127
Top Cited PapersBackdoor attacks and defenses in federated learning: Survey, challenges and future research directions