paper-with-me

홈 › Papers

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, we extend this line of work to "lazy training" of neural networks -- a dominant model in deep learning theory in which neural networks are provably efficiently learnable. We show that over-parametrized neural networks that are guaranteed to generalize well and enjoy strong computational guarantees remain vulnerable to attacks generated using a single step of gradient ascent.

📄 PDF Abstract BibTeX arXiv:2207.00411

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessLearning Theory

Similar Papers 제목 키워드 기반

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes

2022-03-22 · Elvis Dohmatob, Alberto Bietti

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand th…

Adversarial Robustness

Evolution of Neural Tangent Kernels under Benign and Adversarial Training

2022-10-21 · Noel Loo, Ramin Hasani, Alexander Amini, Daniela Rus

Two key challenges facing modern deep learning are mitigating deep networks' vulnerability to adversarial attacks and understanding deep learning's generalization capabilities. Towards the first issue, many defense strat…

Adversarial Robustness

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

2021-06-18 · ICMLW 2021 6 · Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli

While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Ye…

Adversarial DefenseAdversarial RobustnessRobust classification

Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

2021-09-29 · ICLR 2022 4 · Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli

While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Ye…

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

2022-09-15 · Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has …