paper-with-me

홈 › Papers

Adversarially Training for Audio Classifiers

2020-08-26 · Raymel Alfonso Sallo, Mohammad Esmaeilpour, Patrick Cardinal

In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks. We firstly show that, the ResNet-56 model trained on the 2D representation of the discrete wavelet transform appended with the tonnetz chromagram outperforms other models in terms of recognition accuracy. Then we demonstrate the positive impact of adversarially training on this model as well as other deep architectures against six types of attack algorithms (white and black-box) with the cost of the reduced recognition accuracy and limited adversarial perturbation. We run our experiments on two benchmarking environmental sound datasets and show that without any imposed limitations on the budget allocations for the adversary, the fooling rate of the adversarially trained models can exceed 90\%. In other words, adversarial attacks exist in any scales, but they might require higher adversarial perturbations compared to non-adversarially trained models.

📄 PDF Abstract BibTeX arXiv:2008.11618

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

Designing Adversarially Resilient Classifiers using Resilient Feature Engineering

2018-12-17 · Kevin Eykholt, Atul Prakash

We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by …

Feature EngineeringGeneral Classification

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

2019-06-09 · NeurIPS 2019 12 · Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang 외

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, …

Adversarial AttackAdversarial DefenseDeep Learning

Benign Overfitting in Adversarially Robust Linear Classification

2021-12-31 · Jinghui Chen, Yuan Cao, Quanquan Gu

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon…

Classification

Towards Understanding the Generative Capability of Adversarially Robust Classifiers

2021-08-20 · ICCV 2021 10 · Yao Zhu, Jiacheng Ma, Jiacheng Sun, Zewei Chen 외

Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a…

Image Generation

Adversarially robust transfer learning

2019-05-20 · ICLR 2020 1 · Ali Shafahi, Parsa Saadatpanah, Chen Zhu, Amin Ghiasi 외

Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to p…

Lifelong learningTransfer Learning