Detection of Adversarial Attacks on Super-Resolvers Using Spectral Features

Summary

Researchers propose a spectral detection method for finding adversarial attacks embedded in super-resolution model weights, a preprocessing component of imaging pipelines. The method trains an XGBoost detector on the radially-averaged power spectral density and benchmarks it against magnitude- and phase-based Fourier spectrum detectors across training and cross-architecture scenarios. The proposed detector outperforms the comparison detectors in most scenarios, and high-frequency features prove most informative for detecting AdvSR attacks.

Topics

• Adversarial machine learning

Related items

• InfoStrong evasive backdoor attacks and an ensemble defenseSimilar attack · OpenAlex (peer-reviewed AI security)
• LowGNN-Guided Selection of Benign-like Anomalies for Backdoor Attacks Against Network Intrusion Detection SystemsSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoRolling the cyber dice with open-source and open-weight AI modelsSimilar attack · CSO Online
• InfoAEGIS: Real-Time Latent-Space Backdoor Detection for Dependable and Secure Small Language Model InferenceSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoHFL-Deflect: Defence framework against adaptive coordinated poisoning attacks in hierarchical federated learningSimilar attack · Elsevier Security Journals