Related papers: Efficient Model-Based Purification Against Adversa…
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…
Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…
Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suitable pre-processing.…
The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations…
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…
Automated driving systems rely on 3D object detectors to recognize possible obstacles from LiDAR point clouds. However, recent works show the adversary can forge non-existent cars in the prediction results with a few fake points (i.e.,…
This paper presents a generative adversarial network (GAN) based approach for radar image enhancement. Although radar sensors remain robust for operations under adverse weather conditions, their application in autonomous vehicles (AVs) is…
Deep Learning models are highly susceptible to adversarial manipulations that can lead to catastrophic consequences. One of the most effective methods to defend against such disturbances is adversarial training but at the cost of…
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that…
Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations…
The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…
Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Despite…
Autonomous vehicles (AVs) rely on LiDAR sensors for environmental perception and decision-making in driving scenarios. However, ensuring the safety and reliability of AVs in complex environments remains a pressing challenge. To address this…
In this paper, we propose a novel guided diffusion purification approach to provide a strong defense against adversarial attacks. Our model achieves 89.62% robust accuracy under PGD-L_inf attack (eps = 8/255) on the CIFAR-10 dataset. We…
Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of attack and the classification model, and thus can defend…
Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly…
Diffusion model (DM) based adversarial purification (AP) has proven to be a powerful defense method that can remove adversarial perturbations and generate a purified example without threats. In principle, the pre-trained DMs can only ensure…
Deep neural networks demonstrate impressive performance in visual recognition, but they remain vulnerable to adversarial attacks that is imperceptible to the human. Although existing defense strategies such as adversarial training and…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this…