Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection
This addresses safety concerns in machine learning by improving certified and adversarial robustness for OOD detection, applicable across network architectures without extra training, though it appears incremental.
The paper tackles the problem of certifying robustness for out-of-distribution (OOD) detection against adversarial attacks, achieving an average increase of ~13% on CIFAR10 and ~5% on CIFAR100 in OOD detection metrics compared to previous methods.
As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an "Out-Of-Distribution" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a $\ell_2$-norm around the input, regardless of network architecture and without the need for specific components or additional training. Further, we improve current techniques for detecting adversarial attacks on OOD samples, while providing high levels of certified and adversarial robustness on in-distribution samples. The average of all OOD detection metrics on CIFAR10/100 shows an increase of $\sim 13 \% / 5\%$ relative to previous approaches.