AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense
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 purification networks, where AID-purifier is a competitive candidate that is light and robust.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseSimilar Papers 제목 키워드 기반
Adversarial Masked Autoencoder Purifier with Defense Transferability
The study of adversarial defense still struggles to combat with advanced adversarial attacks. In contrast to most prior studies that rely on the diffusion model for test-time defense to remarkably increase the inference …
Adversarial DefenseAdversarial RobustnessMalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent…
Adversarial PurificationAndroid Malware DetectionDenoisingMalware Detection+1Purifier: Defending Data Inference Attacks via Transforming Confidence Scores
Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful informat…
AttributeInference AttackMembership Inference AttackPuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters.…
Adversarial PurificationSelf-supervised Adversarial Purification for Graph Neural Networks
Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicti…