paper-with-me

Papers

Stratified Adversarial Robustness with Rejection

2023-05-02 · Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu, YIngyu Liang, Somesh Jha

Recently, there is an emerging interest in adversarially training a classifier with a rejection option (also known as a selective classifier) for boosting adversarial robustness. While rejection can incur a cost in many applications, existing studies typically associate zero cost with rejecting perturbed inputs, which can result in the rejection of numerous slightly-perturbed inputs that could be correctly classified. In this work, we study adversarially-robust classification with rejection in the stratified rejection setting, where the rejection cost is modeled by rejection loss functions monotonically non-increasing in the perturbation magnitude. We theoretically analyze the stratified rejection setting and propose a novel defense method -- Adversarial Training with Consistent Prediction-based Rejection (CPR) -- for building a robust selective classifier. Experiments on image datasets demonstrate that the proposed method significantly outperforms existing methods under strong adaptive attacks. For instance, on CIFAR-10, CPR reduces the total robust loss (for different rejection losses) by at least 7.3% under both seen and unseen attacks.

📄 PDF Abstract BibTeX arXiv:2305.01139

Code (1)

jfc43/stratified-adv-rej 공식 구현 pytorch

Tasks

Adversarial RobustnessRobust classification

Similar Papers 제목 키워드 기반

Revisiting Adversarial Robustness of Classifiers With a Reject Option

2021-11-22 · AAAI Workshop AdvML 2022 2 · Jiefeng Chen, Jayaram Raghuram, Jihye Choi, Xi Wu 외

Adversarial training of deep neural networks (DNNs) is an important defense mechanism that allows a DNN to be robust to input perturbations, that can otherwise result in predictions errors. Recently, there is a growing i…

Adversarial Robustnessimage-classificationImage Classification

Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart

2021-05-31 · CVPR 2022 1 · Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong 외

Correctly classifying adversarial examples is an essential but challenging requirement for safely deploying machine learning models. As reported in RobustBench, even the state-of-the-art adversarially trained models stru…

Vocal Bursts Valence Prediction

Adversarial Defense by Stratified Convolutional Sparse Coding

2018-11-30 · CVPR 2019 6 · Bo Sun, Nian-hsuan Tsai, Fangchen Liu, Ronald Yu 외

We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbati…

Adversarial Defense

Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection

2023-05-27 · Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen 외

Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Tram\`er showed that, in the rejection-only case (no transduction), a strong rejectio…

Adversarial Robustness

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

2023-02-17 · Luke E. Richards, Edward Raff, Cynthia Matuszek

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do these defenses defend? This work considers …

Adversarial RobustnessFairnessspeech-recognitionSpeech Recognition