相关论文: Certified Defences Against Adversarial Patch Attac…

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonomous driving, content moderation, biometric authentication,…

Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate…

We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certification that correctly accounts for multiple testing,…

Deep learning interpretation is essential to explain the reasoning behind model predictions. Understanding the robustness of interpretation methods is important especially in sensitive domains such as medical applications since…

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious…

Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single physically-realizable adversarial patch to make the…

Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an adversarial attack. This is a problem combined with the…

As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such attacks, they typically assume that all adversarial…

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified…

Object detection is fundamental to various real-world applications, such as security monitoring and surveillance video analysis. Despite their advancements, state-of-the-art object detectors are still vulnerable to adversarial patch…

We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks. This method, for instance, allows public vision API providers and users to seamlessly convert pretrained non-robust…

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…

Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against…

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models…

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…