paper-with-me

Papers

Fooling Adversarial Training with Induction Noise

2021-09-29 · Zhirui Wang, Yifei Wang, Yisen Wang

Adversarial training is widely believed to be a reliable approach to improve model robustness against adversarial attack. However, in this paper, we show that when trained on one type of poisoned data, adversarial training can also be fooled to have catastrophic behavior, e.g., $<1\%$ robust test accuracy with $>90\%$ robust training accuracy on CIFAR-10 dataset. Previously, there are other types of noise poisoned in the training data that have successfully fooled standard training ($15.8\%$ standard test accuracy with $99.9\%$ standard training accuracy on CIFAR-10 dataset), but their poisonings can be easily removed when adopting adversarial training. Therefore, we aim to design a new type of inducing noise, named ADVIN, which is an irremovable poisoning of training data. ADVIN can not only degrade the robustness of adversarial training by a large margin, for example, from $51.7\%$ to $0.57\%$ on CIFAR-10 dataset, but also be effective for fooling standard training ($13.1\%$ standard test accuracy with $100\%$ standard training accuracy). Additionally, ADVIN can be applied to preventing personal data (like selfies) from being exploited without authorization under whether standard or adversarial training.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Fooling Adversarial Training with Inducing Noise

2021-11-19 · Zhirui Wang, Yifei Wang, Yisen Wang

Adversarial training is widely believed to be a reliable approach to improve model robustness against adversarial attack. However, in this paper, we show that when trained on one type of poisoned data, adversarial traini…

Adversarial Attack

There is more than one kind of robustness: Fooling Whisper with adversarial examples

2022-10-26 · Raphael Olivier, Bhiksha Raj

Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversa…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Sentencespeech-recognition+1

A Two-Stage Data-Free Adversarial Patch Generation Framework

2021-09-29 · Jiawei Liu, Hang Gao, Yunfeng Hu, Xun Gong

General adversarial patch generation (APG) methods rely on training datasets of target models and are not applicable to data-free scenarios. This article presents a two-stage APG framework that exploits a determined prox…

Vocal Bursts Valence Prediction

DiffGradCAM: A Universal Class Activation Map Resistant to Adversarial Training

2025-06-10 · Jacob Piland, Chris Sweet, Adam Czakja

Class Activation Mapping (CAM) and its gradient-based variants (e.g., GradCAM) have become standard tools for explaining Convolutional Neural Network (CNN) predictions. However, these approaches typically focus on indivi…

Training Universal Adversarial Perturbations with Alternating Loss Functions

2021-11-22 · AAAI Workshop AdvML 2022 2 · Deniz Sen, Berat Tuna Karli, Alptekin Temizel

Despite being very successful, deep learning models were shown to be vulnerable to crafted perturbations. Furthermore, changing the prediction of a network over any image by learning a single universal adversarial pertur…