Related papers: UniAda: Universal Adaptive Multi-objective Adversa…
Distributed learning frameworks, which partition neural network models across multiple computing nodes, enhance efficiency in collaborative edge-cloud systems, but may also introduce new vulnerabilities to evasion attacks, often in the form…
Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…
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…
Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some…
The susceptibility of deep neural networks (DNNs) to adversarial examples has prompted an increase in the deployment of adversarial attacks. Image-agnostic universal adversarial perturbations (UAPs) are much more threatening, but many…
Deep learning-based time series models are being extensively utilized in engineering and manufacturing industries for process control and optimization, asset monitoring, diagnostic and predictive maintenance. These models have shown great…
Drivers are becoming increasingly reliant on advanced driver assistance systems (ADAS) as autonomous driving technology becomes more popular and developed with advanced safety features to enhance road safety. However, the increasing…
Adversarial perturbations pose a significant threat to deep learning models. Adversarial Training (AT), the predominant defense method, faces challenges of high computational costs and a degradation in standard performance. While data…
Autonomous UAV navigation using reinforcement learning (RL) is vulnerable to adversarial attacks that manipulate sensor inputs, potentially leading to unsafe behavior and mission failure. Although robust RL methods provide partial…
Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…
Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against…
Adversarial attacks on deep learning models have proliferated in recent years. In many cases, a different adversarial perturbation is required to be added to each image to cause the deep learning model to misclassify it. This is ineffective…
Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before…
End-to-end autonomous driving systems have achieved significant progress, yet their adversarial robustness remains largely underexplored. In this work, we conduct a closed-loop evaluation of state-of-the-art autonomous driving agents under…
Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may…
Reliable detection of various objects and road users in the surrounding environment is crucial for the safe operation of automated driving systems (ADS). Despite recent progresses in developing highly accurate object detectors based on Deep…
Nowadays, intrusion detection systems based on deep learning deliver state-of-the-art performance. However, recent research has shown that specially crafted perturbations, called adversarial examples, are capable of significantly reducing…
While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gained great attention.…
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…
Unsupervised Domain Adaptation (UDA) is a key issue in visual recognition, as it allows to bridge different visual domains enabling robust performances in the real world. To date, all proposed approaches rely on human expertise to manually…