Related papers: Evaluating the Robustness of Off-Road Autonomous D…

Nowadays, autonomous driving has attracted much attention from both industry and academia. Convolutional neural network (CNN) is a key component in autonomous driving, which is also increasingly adopted in pervasive computing such as…

Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes, as the coarse-grained road detection can not satisfy off-road vehicles with various mechanical properties.…

Recent research efforts on 3D point cloud semantic segmentation (PCSS) have achieved outstanding performance by adopting neural networks. However, the robustness of these complex models have not been systematically analyzed. Given that PCSS…

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

The classification of road signs by autonomous systems, especially those reliant on visual inputs, is highly susceptible to adversarial attacks. Traditional approaches to mitigating such vulnerabilities have focused on enhancing the…

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust in the inference…

Semantic segmentation is a significant perception task in autonomous driving. It suffers from the risks of adversarial examples. In the past few years, deep learning has gradually transitioned from convolutional neural network (CNN) models…

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine-learning-based systems,…

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation…

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with…

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly vulnerable to inputs being mildly perturbed by adversarial…

Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous…

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…

State-of-the-art convolutional neural networks excel in machine learning tasks such as face recognition, and object classification but suffer significantly when adversarial attacks are present. It is crucial that machine critical systems,…

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

Deep learning models have proven to be successful in a wide range of machine learning tasks. Yet, they are often highly sensitive to perturbations on the input data which can lead to incorrect decisions with high confidence, hampering their…

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we…

Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat…