Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body of research has been devoted to improving the model robustness. However, providing provable robustness guarantees instead of empirical robustness is still widely unexplored. In this paper, we propose Text-CRS, a generalized certified robustness framework for natural language processing (NLP) based on randomized smoothing. To our best knowledge, existing certified schemes for NLP can only certify the robustness against $\ell_0$ perturbations in synonym substitution attacks. Representing each word-level adversarial operation (i.e., synonym substitution, word reordering, insertion, and deletion) as a combination of permutation and embedding transformation, we propose novel smoothing theorems to derive robustness bounds in both permutation and embedding space against such adversarial operations. To further improve certified accuracy and radius, we consider the numerical relationships between discrete words and select proper noise distributions for the randomized smoothing. Finally, we conduct substantial experiments on multiple language models and datasets. Text-CRS can address all four different word-level adversarial operations and achieve a significant accuracy improvement. We also provide the first benchmark on certified accuracy and radius of four word-level operations, besides outperforming the state-of-the-art certification against synonym substitution attacks.

Certifiable Black-Box Attack: Ensuring Provably Successful Attack for Adversarial Examples

Black-box adversarial attacks have shown strong potential to subvert machine learning models. Existing black-box adversarial attacks craft the adversarial examples by iteratively querying the target model and/or leveraging the transferability of a local surrogate model. Whether such attack can succeed remains unknown to the adversary when empirically designing the attack. In this paper, to our best knowledge, we take the first step to study a new paradigm of adversarial attacks -- certifiable black-box attack that can guarantee the attack success rate of the crafted adversarial examples. Specifically, we revise the randomized smoothing to establish novel theories for ensuring the attack success rate of the adversarial examples. To craft the adversarial examples with the certifiable attack success rate (CASR) guarantee, we design several novel techniques, including a randomized query method to query the target model, an initialization method with smoothed self-supervised perturbation to derive certifiable adversarial examples, and a geometric shifting method to reduce the perturbation size of the certifiable adversarial examples for better imperceptibility. We have comprehensively evaluated the performance of the certifiable black-box attack on CIFAR10 and ImageNet datasets against different levels of defenses. Both theoretical and experimental results have validated the effectiveness of the proposed certifiable attack.

Certified Adversarial Robustness via Anisotropic Randomized Smoothing

Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbed input with provable robustness bound by injecting noise into the classifier. However, all of the existing methods rely on fixed i.i.d. probability distribution to generate noise for all dimensions of the data (e.g., all the pixels in an image), which ignores the heterogeneity of inputs and data dimensions. Thus, existing randomized smoothing methods cannot provide optimal protection for all the inputs. To address this limitation, we propose the first anisotropic randomized smoothing method which ensures provable robustness guarantee based on pixel-wise noise distributions. Also, we design a novel CNN-based noise generator to efficiently fine-tune the pixel-wise noise distributions for all the pixels in each input. Experimental results demonstrate that our method significantly outperforms the state-of-the-art randomized smoothing methods.

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 the robustness certification of any input on any classifier against any $\ell_p$ perturbations with noise generated by any continuous probability distribution. Compared with the state-of-the-art certified defenses, UniCR provides many significant benefits: (1) the first universal robustness certification framework for the above 4 'any's; (2) automatic robustness certification that avoids case-by-case analysis, (3) tightness validation of certified robustness, and (4) optimality validation of noise distributions used by randomized smoothing. We conduct extensive experiments to validate the above benefits of UniCR and the advantages of UniCR over state-of-the-art certified defenses against $\ell_p$ perturbations.

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which contains critical information for generating malicious perturbations. In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks. By using both gradient maps and adversarial images as inputs, we propose a Two-stream Restoration Network (TRN) to restore the adversarial images. To optimally restore the perturbed images with two streams of inputs, a Gradient Map Estimation Mechanism is proposed to estimate the gradients of adversarial images, and a Fusion Block is designed in TRN to explore and fuse the information in two streams. Once trained, our TRN can defend against a wide range of attack methods without significantly degrading the performance of benign inputs. Also, our method is generalizable, scalable, and hard to bypass. Experimental results on CIFAR10, SVHN, and Fashion MNIST demonstrate that our method outperforms state-of-the-art defense methods.