Related papers: Adversarial attacks and defenses in Speaker Recogn…
Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles,…
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
There is great potential for damage from adversarial learning (AL) attacks on machine-learning based systems. In this paper, we provide a contemporary survey of AL, focused particularly on defenses against attacks on statistical…
Adversaries are often able to penetrate networks and compromise systems by exploiting vulnerabilities in people and systems. The key to the success of these attacks is information that adversaries collect throughout the phases of the cyber…
Learning-based pattern classifiers, including deep networks, have shown impressive performance in several application domains, ranging from computer vision to cybersecurity. However, it has also been shown that adversarial input…
Deep learning models have been used for a wide variety of tasks. They are prevalent in computer vision, natural language processing, speech recognition, and other areas. While these models have worked well under many scenarios, it has been…
Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on…
Machine learning (ML) models serve as powerful tools for threat detection and mitigation; however, they also introduce potential new risks. Adversarial input can exploit these models through standard interfaces, thus creating new attack…
As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…
Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…
Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited embedded platforms…
Deep learning solutions are instrumental in cybersecurity, harnessing their ability to analyze vast datasets, identify complex patterns, and detect anomalies. However, malevolent actors can exploit these capabilities to orchestrate…
With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…
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…
As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought.…
Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the…
Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…
Advances in deep learning have enabled the widespread deployment of speaker recognition systems (SRSs), yet they remain vulnerable to score-based impersonation attacks. Existing attacks that operate directly on raw waveforms require a large…