Towards Certification of Uncertainty Calibration under Adversarial Attacks
Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable guarantees on the insensitivity of their predictions to such perturbations. Furthermore, in safety-critical applications, the frequentist interpretation of the confidence of a classifier (also known as model calibration) can be of utmost importance. This property can be measured via the Brier score or the expected calibration error. We show that attacks can significantly harm calibration, and thus propose certified calibration as worst-case bounds on calibration under adversarial perturbations. Specifically, we produce analytic bounds for the Brier score and approximate bounds via the solution of a mixed-integer program on the expected calibration error. Finally, we propose novel calibration attacks and demonstrate how they can improve model calibration through \textit{adversarial calibration training}.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications ca…
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
It is widely known that state-of-the-art machine learning models, including vision and language models, can be seriously compromised by adversarial perturbations. It is therefore increasingly relevant to develop capabili…
Adversarial AttackBayesian OptimizationUncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks
Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial atta…
Adversarial RobustnessAutonomous DrivingAutonomous VehiclesConformal Prediction+4Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms
Methods for adversarial robustness certification aim to provide an upper bound on the test error of a classifier under adversarial manipulation of its input. Current certification methods are computationally expensive an…
Adversarial RobustnessQuantizationTripletCalibrating Uncertainty for Zero-Shot Adversarial CLIP
CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks. Prior adversarial fine-tuning work primarily matches predicted logits between clean and adversarial examples, which over…
Zero-shot GeneralizationAdversarial Robustness