paper-with-me

홈 › Papers

Label Smoothing and Adversarial Robustness

2020-09-17 · Chaohao Fu, Hongbin Chen, Na Ruan, Weijia Jia

Recent studies indicate that current adversarial attack methods are flawed and easy to fail when encountering some deliberately designed defense. Sometimes even a slight modification in the model details will invalidate the attack. We find that training model with label smoothing can easily achieve striking accuracy under most gradient-based attacks. For instance, the robust accuracy of a WideResNet model trained with label smoothing on CIFAR-10 achieves 75% at most under PGD attack. To understand the reason underlying the subtle robustness, we investigate the relationship between label smoothing and adversarial robustness. Through theoretical analysis about the characteristics of the network trained with label smoothing and experiment verification of its performance under various attacks. We demonstrate that the robustness produced by label smoothing is incomplete based on the fact that its defense effect is volatile, and it cannot defend attacks transferred from a naturally trained model. Our study enlightens the research community to rethink how to evaluate the model's robustness appropriately.

📄 PDF Abstract BibTeX arXiv:2009.08233

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial Robustness

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Batch Normalization 설명 없음
Residual Connection 설명 없음
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…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Wide Residual Block 설명 없음
Kaiming Initialization 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

2022-12-20 · Yahan Yang, Soham Dan, Dan Roth, Insup Lee

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substit…

Adversarial Robustness

Adversarial Robustness via Label-Smoothing

2019-06-27 · Morgane Goibert, Elvis Dohmatob

We study Label-Smoothing as a means for improving adversarial robustness of supervised deep-learning models. After establishing a thorough and unified framework, we propose several variations to this general method: adve…

Adversarial Robustness

Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?

2019-10-25 · Ali Shafahi, Amin Ghiasi, Furong Huang, Tom Goldstein

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples du…

Adversarial Robustness

Adversarial Robustness via Adaptive Label Smoothing

2021-09-29 · Qibing Ren, Liangliang Shi, Lanjun Wang, Junchi Yan

Adversarial training (AT) has become a dominant defense paradigm by enforcing the model's predictions to be locally invariant to adversarial examples. Being a simple technique, Label smoothing (LS) has shown its potentia…

Adversarial Robustness

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

2024-07-16 · Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu 외

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized…

Adversarial Robustness