Deploying Adversarial Attacks in Super-Resolution Models
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Farragut High School, Knoxville, TN (United States)
Reliable super-resolution methods are crucial for applications like remote sensing, grid resilience and disaster impact analysis, and standoff biometrics. These methods infuse additional high-frequency information into reconstructions, allowing for better contextualization and image intelligence. However, super-resolution models can also introduce hallucinations or other unseen vulnerabilities that could be exploited by an adversary. This is further compounded by the prominence of deep learning in these models, as models are often blindly applied on out-of-distribution images. In this work, we implement adversarial attacks in common open-source super-resolution models and examine their impact on reconstructions and downstream classification tasks. We find that an adversarially trained super-resolution model can produce high-quality reconstructions that degrade downstream classifications. Moreover, these attacks do not require access to low-resolution imagery or class labels at inference time. These results demonstrate the vulnerability of super-resolution methods to malicious actors and motivates the development of a detector for super-resolution adversarial attacks. Further exploration of adversarial attacks in this domain is required to ensure trustworthiness and robustness of super-resolution models for national security applications.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC)
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 3002016
- Report Number(s):
- ORNL/TM--2025/4263
- Country of Publication:
- United States
- Language:
- English
Similar Records
Attack on Grid Event Cause Analysis: An Adversarial Machine Learning Approach
Cyber Attack Sequences Generation for Electric Power Grid
Taxonomies of Cyber Adversaries and Attacks: A Survey of Incidents and Approaches
Conference
·
Fri Jan 31 23:00:00 EST 2020
· 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT)
·
OSTI ID:1958805
Cyber Attack Sequences Generation for Electric Power Grid
Conference
·
Tue May 03 00:00:00 EDT 2022
·
OSTI ID:1872531
Taxonomies of Cyber Adversaries and Attacks: A Survey of Incidents and Approaches
Technical Report
·
Thu Oct 08 00:00:00 EDT 2009
·
OSTI ID:967712