Samuel Sasaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Samuel Sasaki has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Taylor Thomas Johnson
Vanderbilt University
3 shared publications - Preston K. Robinette
Vanderbilt University
2 shared publications - Thuy Dung Nguyen
Vanderbilt University
2 shared publications - Anne Marie Tumlin
Vanderbilt University
1 shared publication - Ben Wooding
Vanderbilt University
1 shared publication - Diego Manzanas Lopez
Vanderbilt University
1 shared publication
Latest Publications
- 18 July 2026
- Published by Springer Nature
- p. 394-400
n2v: Neural Network Verification in Python (Competition Contribution)
- 18 July 2026
- Published by Springer Nature
- p. 394-400
n2v: Neural Network Verification in Python (Competition Contribution)
- 28 October 2025
- Published by Springer Nature
- p. 260-265
NNV: A Star Set Reachability Approach (Competition Contribution)
- 28 October 2025
- Published by Springer Nature
- p. 260-265
NNV: A Star Set Reachability Approach (Competition Contribution)
- 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
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.