相关论文: PatchZero: Defending against Adversarial Patch Att…

Adversarial examples present significant challenges to the security of Deep Neural Network (DNN) applications. Specifically, there are patch-based and texture-based attacks that are usually used to craft physical-world adversarial examples,…

Deep neural networks (DNNs) are vulnerable to various types of adversarial examples, bringing huge threats to security-critical applications. Among these, adversarial patches have drawn increasing attention due to their good applicability…

Deep neural networks were applied with success in a myriad of applications, but in safety critical use cases adversarial attacks still pose a significant threat. These attacks were demonstrated on various classification and detection tasks…

Object detection is a fundamental task in various applications ranging from autonomous driving to intelligent security systems. However, recognition of a person can be hindered when their clothing is decorated with carefully designed…

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…

Realistic adversarial attacks on various camera-based perception tasks of autonomous vehicles have been successfully demonstrated so far. However, only a few works considered attacks on traffic light detectors. This work shows how CNNs for…

Recently, there has been a lot of progress in reducing the computation of deep models at inference time. These methods can reduce both the computational needs and power usage of deep models. Some of these approaches adaptively scale the…

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted more attention. Many algorithms have been proposed to craft powerful adversarial examples. However, most of these algorithms modified the global or local…

Despite the outstanding performance of deep neural networks, they are vulnerable to adversarial attacks. While there are many invisible attacks in the digital domain, most physical world adversarial attacks are visible. Here we present an…

State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time…

Face recognition is greatly improved by deep convolutional neural networks (CNNs). Recently, these face recognition models have been used for identity authentication in security sensitive applications. However, deep CNNs are vulnerable to…

Object detection is a crucial task in autonomous driving. While existing research has proposed various attacks on object detection, such as those using adversarial patches or stickers, the exploration of projection attacks on 3D surfaces…

We present Vax-a-Net; a technique for immunizing convolutional neural networks (CNNs) against adversarial patch attacks (APAs). APAs insert visually overt, local regions (patches) into an image to induce misclassification. We introduce a…

With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-world usage is to append adversarial patches (e.g. logos) to…

Adversarial attacks on face recognition (FR) systems pose a significant security threat, yet most are confined to the digital domain or require white-box access. We introduce GaP (Gaussian Patch), a novel method to generate a universal,…

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating…

Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from these images. Previous methods to prevent OCR piracy by…

Autonomous flying robots, e.g. multirotors, often rely on a neural network that makes predictions based on a camera image. These deep learning (DL) models can compute surprising results if applied to input images outside the training…

It is well-known that the most existing machine learning (ML)-based safety-critical applications are vulnerable to carefully crafted input instances called adversarial examples (AXs). An adversary can conveniently attack these target…

Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although…