paper-with-me

Papers

Composite Adversarial Training for Multiple Adversarial Perturbations and Beyond

2021-01-01 · Xinyang Zhang, Zheng Zhang, Ting Wang

One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial perturbations. Despite the plethora of work on defending against individual perturbation models, improving DNN robustness against the combinations of multiple perturbations is still fairly under-studied. In this paper, we propose \underline{c}omposite \underline{a}dversarial \underline{t}raining (CAT), a novel training method that flexibly integrates and optimizes multiple adversarial losses, leading to significant robustness improvement with respect to individual perturbations as well as their ``compositions''. Through empirical evaluation on benchmark datasets and models, we show that CAT outperforms existing adversarial training methods by large margins in defending against the compositions of pixel perturbations and spatial transformations, two major classes of adversarial perturbation models, while incurring limited impact on clean inputs.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalizing Adversarial Training to Composite Semantic Perturbations

2021-06-18 · ICML Workshop AML 2021 7 · Yun-Yun Tsai, Lei Hsiung, Pin-Yu Chen, Tsung-Yi Ho

Model robustness against adversarial examples has been widely studied, yet the lack of generalization to more realistic scenarios can be challenging. Specifically, recent works using adversarial training can successfully…

Scheduling

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations

2022-02-09 · CVPR 2023 1 · Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho

Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations …

Adversarial RobustnessScheduling

CARBEN: Composite Adversarial Robustness Benchmark

2022-07-16 · Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho

Prior literature on adversarial attack methods has mainly focused on attacking with and defending against a single threat model, e.g., perturbations bounded in Lp ball. However, multiple threat models can be combined int…

Adversarial AttackAdversarial Robustness

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

2023-07-13 · Jialiang Sun, Wen Yao, Tingsong Jiang, Xiaoqian Chen

Deep neural networks have proven to be vulnerable to adversarial attacks in the form of adding specific perturbations on images to make wrong outputs. Designing stronger adversarial attack methods can help more reliably …

Adversarial AttackAutoML

A Study on Adversarial Robustness of Discriminative Prototypical Learning

2025-04-03 · Ramin Zarei Sabzevar, Hamed Mohammadzadeh, Tahmineh Tavakoli, Ahad Harati

Deep neural networks demonstrate significant vulnerability to adversarial perturbations, posing risks for critical applications. Current adversarial training methods predominantly focus on robustness against attacks with…

Adversarial Robustness