paper-with-me

홈 › Papers

Enhanced countering adversarial attacks via input denoising and feature restoring

2021-11-19 · Yanni Li, Wenhui Zhang, Jiawei Liu, Xiaoli Kou, Hui Li, Jiangtao Cui

Despite the fact that deep neural networks (DNNs) have achieved prominent performance in various applications, it is well known that DNNs are vulnerable to adversarial examples/samples (AEs) with imperceptible perturbations in clean/original samples. To overcome the weakness of the existing defense methods against adversarial attacks, which damages the information on the original samples, leading to the decrease of the target classifier accuracy, this paper presents an enhanced countering adversarial attack method IDFR (via Input Denoising and Feature Restoring). The proposed IDFR is made up of an enhanced input denoiser (ID) and a hidden lossy feature restorer (FR) based on the convex hull optimization. Extensive experiments conducted on benchmark datasets show that the proposed IDFR outperforms the various state-of-the-art defense methods, and is highly effective for protecting target models against various adversarial black-box or white-box attacks. \footnote{Souce code is released at: \href{https://github.com/ID-FR/IDFR}{https://github.com/ID-FR/IDFR}}

📄 PDF Abstract BibTeX arXiv:2111.10075

Code (1)

id-fr/idfr 공식 구현 tf

Tasks

Adversarial AttackDenoising

Similar Papers 제목 키워드 기반

Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks

2019-08-21 · Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, Ling Liu

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to…

DenoisingDiversity

Combating Adversaries with Anti-Adversaries

2021-03-26 · ICML Workshop AML 2021 7 · Motasem Alfarra, Juan C. Pérez, Ali Thabet, Adel Bibi 외

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the tru…

Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset

2025-02-12 · Vladimir Frants, Sos Agaian

This paper addresses the vulnerability of deep-learning models designed for rain, snow, and haze removal. Despite enhancing image quality in adverse weather, these models are susceptible to adversarial attacks that compr…

Denoisingimage-classificationImage ClassificationSSIM+1

Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm

2023-03-28 · Bakary Badjie, José Cecílio, António Casimiro

Adversarial attacks significantly threaten the robustness of deep neural networks (DNNs). Despite the multiple defensive methods employed, they are nevertheless vulnerable to poison attacks, where attackers meddle with t…

Adversarial RobustnessData PoisoningDenoising

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks

2024-03-14 · Roey Bokobza, Yisroel Mirsky

Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples. Unlike traditional preprocessing defences that rely on sanitizing input…