Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart
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 struggle to exceed 67% robust test accuracy on CIFAR-10, which is far from practical. A complementary way towards robustness is to introduce a rejection option, allowing the model to not return predictions on uncertain inputs, where confidence is a commonly used certainty proxy. Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled rejection metrics, which could provably distinguish wrongly classified inputs from correctly classified ones. This intriguing property sheds light on using coupling strategies to better detect and reject adversarial examples. We evaluate our rectified rejection (RR) module on CIFAR-10, CIFAR-10-C, and CIFAR-100 under several attacks including adaptive ones, and demonstrate that the RR module is compatible with different adversarial training frameworks on improving robustness, with little extra computation. The code is available at https://github.com/P2333/Rectified-Rejection.
Code (1)
Tasks
Vocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
Learning with Protection: Rejection of Suspicious Samples under Adversarial Environment
We propose a novel framework for avoiding the misclassification of data by using a framework of learning with rejection and adversarial examples. Recent developments in machine learning have opened new opportunities for …
BIG-bench Machine LearningBinary ClassificationDecision MakingMulti-class Classification+1ATRO: Adversarial Training with a Rejection Option
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performanc…
Deep Neural Rejection against Adversarial Examples
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause mis…
Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
Detection and rejection of adversarial examples in security sensitive and safety-critical systems using deep CNNs is essential. In this paper, we propose an approach to augment CNNs with out-distribution learning in orde…
Countermeasures Against Adversarial Examples in Radio Signal Classification
Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks call…
ClassificationDeep Learning