AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense
Duhun Hwang, Eunjung Lee, Wonjong Rhee

TL;DR
AID-Purifier is a lightweight auxiliary network designed to enhance the robustness of adversarially-trained classifiers by purifying inputs, leveraging information maximization and AVmixup for improved adversarial defense.
Contribution
Introduces AID-Purifier, a novel, computationally efficient auxiliary network that boosts adversarial robustness when combined with existing defenses.
Findings
Enhances robustness of adversarially-trained networks
Compatible with other purification methods like PixelDefend
Competitive performance as a lightweight purification network
Abstract
We propose an AID-purifier that can boost the robustness of adversarially-trained networks by purifying their inputs. AID-purifier is an auxiliary network that works as an add-on to an already trained main classifier. To keep it computationally light, it is trained as a discriminator with a binary cross-entropy loss. To obtain additionally useful information from the adversarial examples, the architecture design is closely related to information maximization principles where two layers of the main classification network are piped to the auxiliary network. To assist the iterative optimization procedure of purification, the auxiliary network is trained with AVmixup. AID-purifier can be used together with other purifiers such as PixelDefend for an extra enhancement. The overall results indicate that the best performing adversarially-trained networks can be enhanced by the best performing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Advanced Neural Network Applications
