paper-with-me

홈 › Papers

Certifying Confidence via Randomized Smoothing

2020-09-17 · NeurIPS 2020 12 · Aounon Kumar, Alexander Levine, Soheil Feizi, Tom Goldstein

Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. It uses the probabilities of predicting the top two most-likely classes around an input point under a smoothing distribution to generate a certified radius for a classifier's prediction. However, most smoothing methods do not give us any information about the confidence with which the underlying classifier (e.g., deep neural network) makes a prediction. In this work, we propose a method to generate certified radii for the prediction confidence of the smoothed classifier. We consider two notions for quantifying confidence: average prediction score of a class and the margin by which the average prediction score of one class exceeds that of another. We modify the Neyman-Pearson lemma (a key theorem in randomized smoothing) to design a procedure for computing the certified radius where the confidence is guaranteed to stay above a certain threshold. Our experimental results on CIFAR-10 and ImageNet datasets show that using information about the distribution of the confidence scores allows us to achieve a significantly better certified radius than ignoring it. Thus, we demonstrate that extra information about the base classifier at the input point can help improve certified guarantees for the smoothed classifier. Code for the experiments is available at https://github.com/aounon/cdf-smoothing.

📄 PDF Abstract BibTeX arXiv:2009.08061

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMAPrediction

Similar Papers 제목 키워드 기반

Bridging the Theoretical Gap in Randomized Smoothing

2025-04-03 · Blaise Delattre, Paul Caillon, Quentin Barthélemy, Erwan Fagnou 외

Randomized smoothing has become a leading approach for certifying adversarial robustness in machine learning models. However, a persistent gap remains between theoretical certified robustness and empirical robustness acc…

Adversarial Robustness

Incremental Randomized Smoothing Certification

2023-05-31 · Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh 외

Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifie…

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

A Unified framework for randomized smoothing based certified defenses

2019-09-25 · Tianhang Zheng, Di Wang, Baochun Li, Jinhui Xu

Randomized smoothing, which was recently proved to be a certified defensive technique, has received considerable attention due to its scalability to large datasets and neural networks. However, several important question…

[Re] Double Sampling Randomized Smoothing

2023-06-27 · Aryan Gupta, Sarthak Gupta, Abhay Kumar, Harsh Dugar

This paper is a contribution to the reproducibility challenge in the field of machine learning, specifically addressing the issue of certifying the robustness of neural networks (NNs) against adversarial perturbations. T…