paper-with-me

홈 › Papers

AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense

2021-07-14 · ICML Workshop AML 2021 7 · Duhun Hwang, Eunjung Lee, Wonjong Rhee

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.

📄 PDF Abstract BibTeX arXiv:2107.06456

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Defense

Similar Papers 제목 키워드 기반

Adversarial Masked Autoencoder Purifier with Defense Transferability

2025-01-28 · Yuan-Chih Chen, Chun-Shien Lu

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 Robustness

MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks

2023-12-11 · Yuyang Zhou, Guang Cheng, Zongyao Chen, Shui Yu

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+1

Purifier: Defending Data Inference Attacks via Transforming Confidence Scores

2022-12-01 · Ziqi Yang, Lijin Wang, Da Yang, Jie Wan 외

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 Attack

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks

2024-01-19 · Ping Guo, Xiang Li, Zhiyuan Yang, Xi Lin 외

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 Purification

Self-supervised Adversarial Purification for Graph Neural Networks

2026-05-22 · Woohyun Lee, Hogun Park arxiv

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…