paper-with-me

홈 › Papers

Perturbation Type Categorization for Multiple $\ell_p$ Bounded Adversarial Robustness

2021-01-01 · Pratyush Maini, Xinyun Chen, Bo Li, Dawn Song

Despite the recent advances in $\textit{adversarial training}$ based defenses, deep neural networks are still vulnerable to adversarial attacks outside the perturbation type they are trained to be robust against. Recent works have proposed defenses to improve the robustness of a single model against the union of multiple perturbation types. However, when evaluating the model against each individual attack, these methods still suffer significant trade-offs compared to the ones specifically trained to be robust against that perturbation type. In this work, we introduce the problem of categorizing adversarial examples based on their $\ell_p$ perturbation types. Based on our analysis, we propose $\textit{PROTECTOR}$, a two-stage pipeline to improve the robustness against multiple perturbation types. Instead of training a single predictor, $\textit{PROTECTOR}$ first categorizes the perturbation type of the input, and then utilizes a predictor specifically trained against the predicted perturbation type to make the final prediction. We first theoretically show that adversarial examples created by different perturbation types constitute different distributions, which makes it possible to distinguish them. Further, we show that at test time the adversary faces a natural trade-off between fooling the perturbation type classifier and the succeeding predictor optimized with perturbation specific adversarial training. This makes it challenging for an adversary to plant strong attacks against the whole pipeline. In addition, we demonstrate the realization of this trade-off in deep networks by adding random noise to the model input at test time, enabling enhanced robustness against strong adaptive attacks. Extensive experiments on MNIST and CIFAR-10 show that $\textit{PROTECTOR}$ outperforms prior adversarial training based defenses by over $5\%$, when tested against the union of $\ell_1, \ell_2, \ell_\infty$ attacks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessVocal Bursts Type Prediction

Similar Papers 제목 키워드 기반

Towards Defending Multiple $\ell_p$-norm Bounded Adversarial Perturbations via Gated Batch Normalization

2020-12-03 · Aishan Liu, Shiyu Tang, Xinyun Chen, Lei Huang 외

There has been extensive evidence demonstrating that deep neural networks are vulnerable to adversarial examples, which motivates the development of defenses against adversarial attacks. Existing adversarial defenses typ…

Adversarial Training and Robustness for Multiple Perturbations

2019-04-30 · NeurIPS 2019 12 · Florian Tramèr, Dan Boneh

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and…

Adversarial Robustness

Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis

2022-10-02 · Jiancong Xiao, Zeyu Qin, Yanbo Fan, Baoyuan Wu 외

Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of perturbation e.g., the $\ell_\infty$ attacks)…

Adversarial Robustness

Defending Against Multiple and Unforeseen Adversarial Videos

2020-09-11 · Shao-Yuan Lo, Vishal M. Patel

Adversarial robustness of deep neural networks has been actively investigated. However, most existing defense approaches are limited to a specific type of adversarial perturbations. Specifically, they often fail to offer…

Adversarial RobustnessGeneral ClassificationVideo ClassificationVideo Recognition

Transfer of Adversarial Robustness Between Perturbation Types

2019-05-03 · Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks 외

We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on $L_\infty$ and $L_2$-bounded perturbations, these do no…

Adversarial Robustness