Related papers: SoK: Pitfalls in Evaluating Black-Box Attacks
Self-adaptive systems offer several attack surfaces due to the communication via different channels and the different sensors required to observe the environment. Often, attacks cause safety to be compromised as well, making it necessary to…
Despite the impressive progress in the field of presentation attack detection and multimedia forensics over the last decade, these systems are still vulnerable to attacks in real-life settings. Some of the challenges for existing solutions…
The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…
Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…
Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…
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.…
In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…
Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks…
Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…
Satellite systems are facing an ever-increasing amount of cybersecurity threats as their role in communications, navigation, and other services expands. Recent papers have examined attacks targeting satellites and space systems; however,…
Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…
Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…
Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model.…
The widespread deployment of Deep Learning-based Face Recognition Systems raises many security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world, unconstrained…
The challenge of decision-making under uncertainty in information security has become increasingly important, given the unpredictable probabilities and effects of events in the ever-changing cyber threat landscape. Cyber threat intelligence…
Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The…
Fault Injection is the study of observing how systems behave under unusual stress, environmental or otherwise. In practice, fault injection involves testing the limits of computer systems and finding novel ways to potentially break…
The rapid advancement of artificial intelligence within the realm of cybersecurity raises significant security concerns. The vulnerability of deep learning models in adversarial attacks is one of the major issues. In adversarial machine…