paper-with-me

홈 › Papers

A Mask-Based Adversarial Defense Scheme

2022-04-21 · Weizhen Xu, Chenyi Zhang, Fangzhen Zhao, Liangda Fang

Adversarial attacks hamper the functionality and accuracy of Deep Neural Networks (DNNs) by meddling with subtle perturbations to their inputs.In this work, we propose a new Mask-based Adversarial Defense scheme (MAD) for DNNs to mitigate the negative effect from adversarial attacks. To be precise, our method promotes the robustness of a DNN by randomly masking a portion of potential adversarial images, and as a result, the %classification result output of the DNN becomes more tolerant to minor input perturbations. Compared with existing adversarial defense techniques, our method does not need any additional denoising structure, nor any change to a DNN's design. We have tested this approach on a collection of DNN models for a variety of data sets, and the experimental results confirm that the proposed method can effectively improve the defense abilities of the DNNs against all of the tested adversarial attack methods. In certain scenarios, the DNN models trained with MAD have improved classification accuracy by as much as 20% to 90% compared to the original models that are given adversarial inputs.

📄 PDF Abstract BibTeX arXiv:2204.11837

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial DefenseDenoising

Similar Papers 제목 키워드 기반

Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches

2023-06-22 · Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin 외

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-th…

Robust classification

SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models

2025-05-22 · Hossein Khalili, Seongbin Park, Venkat Bollapragada, Nader Sehatbakhsh

As vision-based machine learning models are increasingly integrated into autonomous and cyber-physical systems, concerns about (physical) adversarial patch attacks are growing. While state-of-the-art defenses can achieve…

Super-Resolution

Defensive Dual Masking for Robust Adversarial Defense

2024-12-10 · Wangli Yang, Jie Yang, Yi Guo, Johan Barthelemy

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle per…

Adversarial Defense

Improving Adversarial Robustness via Decoupled Visual Representation Masking

2024-06-16 · Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang 외

Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing based defense is a major strategy, as well …

Adversarial DefenseAdversarial RobustnessDiversity

MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification

2024-06-18 · Harrison Gietz, Jugal Kalita

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diff…

Adversarial DefenseDenoisingLanguage Modelling