paper-with-me

홈 › Papers

A single gradient step finds adversarial examples on random two-layers neural networks

2021-04-08 · NeurIPS 2021 12 · Sébastien Bubeck, Yeshwanth Cherapanamjeri, Gauthier Gidel, Rémi Tachet des Combes

Daniely and Schacham recently showed that gradient descent finds adversarial examples on random undercomplete two-layers ReLU neural networks. The term "undercomplete" refers to the fact that their proof only holds when the number of neurons is a vanishing fraction of the ambient dimension. We extend their result to the overcomplete case, where the number of neurons is larger than the dimension (yet also subexponential in the dimension). In fact we prove that a single step of gradient descent suffices. We also show this result for any subexponential width random neural network with smooth activation function.

📄 PDF Abstract BibTeX arXiv:2104.03863

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Robust Single-step Adversarial Training with Regularizer

2021-02-05 · Lehui Xie, Yaopeng Wang, Jia-Li Yin, Ximeng Liu

High cost of training time caused by multi-step adversarial example generation is a major challenge in adversarial training. Previous methods try to reduce the computational burden of adversarial training using single-st…

Understanding Catastrophic Overfitting in Single-step Adversarial Training

2020-10-05 · Hoki Kim, Woojin Lee, Jaewook Lee

Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the…

Adversarial Robustness is at Odds with Lazy Training

2022-06-18 · Yunjuan Wang, Enayat Ullah, Poorya Mianjy, Raman Arora

Recent works show that adversarial examples exist for random neural networks [Daniely and Schacham, 2020] and that these examples can be found using a single step of gradient ascent [Bubeck et al., 2021]. In this work, w…

Adversarial RobustnessLearning Theory

Multi-stage Optimization based Adversarial Training

2021-06-26 · Xiaosen Wang, Chuanbiao Song, LiWei Wang, Kun He

In the field of adversarial robustness, there is a common practice that adopts the single-step adversarial training for quickly developing adversarially robust models. However, the single-step adversarial training is mos…

Adversarial Robustness

Single-Step Adversarial Training for Semantic Segmentation

2021-06-30 · Daniel Wiens, Barbara Hammer

Even though deep neural networks succeed on many different tasks including semantic segmentation, they lack on robustness against adversarial examples. To counteract this exploit, often adversarial training is used. Howe…

SegmentationSemantic Segmentation