SoK: Certified Robustness for Deep Neural Networks
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when deploying these models to safety-critical applications such as autonomous driving. Different defense approaches have been proposed against adversarial attacks, including: a) empirical defenses, which can usually be adaptively attacked again without providing robustness certification; and b) certifiably robust approaches, which consist of robustness verification providing the lower bound of robust accuracy against any attacks under certain conditions and corresponding robust training approaches. In this paper, we systematize certifiably robust approaches and related practical and theoretical implications and findings. We also provide the first comprehensive benchmark on existing robustness verification and training approaches on different datasets. In particular, we 1) provide a taxonomy for the robustness verification and training approaches, as well as summarize the methodologies for representative algorithms, 2) reveal the characteristics, strengths, limitations, and fundamental connections among these approaches, 3) discuss current research progresses, theoretical barriers, main challenges, and future directions for certifiably robust approaches for DNNs, and 4) provide an open-sourced unified platform to evaluate 20+ representative certifiably robust approaches.
Code (2)
Tasks
Autonomous DrivingSimilar Papers 제목 키워드 기반
Boosting Certified Robustness of Deep Networks via a Compositional Architecture
A core challenge with existing certified defense mechanisms is that while they improve certified robustness, they also tend to drastically decrease standard accuracy, making it difficult to use these methods in practice.…
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate …
Towards Universal Certified Robustness with Multi-Norm Training
Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. $l_\infty$ or $l_2$). However, an $l_\infty$ certifiably robust model may not be certifiably robust against…
Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses…
On the Extreme Variance of Certified Local Robustness Across Model Seeds
Robustness verification of neural networks, referring to formally proving that neural networks satisfy robustness properties, is of crucial importance in safety-critical applications, where model failures can result in l…