Related papers: Systematic Discovery of Semantic Attacks in Online…

Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break such defenses…

Today's success of state of the art methods for semantic segmentation is driven by large datasets. Data is considered an important asset that needs to be protected, as the collection and annotation of such datasets comes at significant…

The growing realism of AI-generated images produced by recent GAN and diffusion models has intensified concerns over the reliability of visual media. Yet, despite notable progress in deepfake detection, current forensic systems degrade…

Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question…

Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However,…

Recently, Deep Neural Networks (DNNs) have achieved remarkable performances in many applications, while several studies have enhanced their vulnerabilities to malicious attacks. In this paper, we emulate the effects of natural weather…

Deep neural networks (DNNs) are increasingly integrated into LiDAR (Light Detection and Ranging)-based perception systems for autonomous vehicles (AVs), requiring robust performance under adversarial conditions. We aim to address the…

Autonomous driving perceives surroundings with line-of-sight sensors that are compromised under environmental uncertainties. To achieve real time global information in high definition map, we investigate to share perception information…

Deep neural networks (DNNs) are vulnerable to adversarial perturbation, where an imperceptible perturbation is added to the image that can fool the DNNs. Diffusion-based adversarial purification focuses on using the diffusion model to…

In light of the significant progress made in the development and application of semantic segmentation tasks, there has been increasing attention towards improving the robustness of segmentation models against natural degradation factors…

Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target mostly monocular perception. Therefore, the effectiveness…

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…

For autonomous driving, an essential task is to detect surrounding objects accurately. To this end, most existing systems use optical devices, including cameras and light detection and ranging (LiDAR) sensors, to collect environment data in…

Adversarial attacks hamper the decision-making ability of neural networks by perturbing the input signal. The addition of calculated small distortion to images, for instance, can deceive a well-trained image classification network. In this…

Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet…

Degradation-agnostic image restoration aims to handle diverse corruptions with one unified model, but faces fundamental challenges in balancing efficiency and performance across different degradation types. Existing approaches either…

Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image.…

Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have…

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked…

LiDAR point clouds collected from a moving vehicle are functions of its trajectories, because the sensor motion needs to be compensated to avoid distortions. When autonomous vehicles are sending LiDAR point clouds to deep networks for…