Related papers: Robust and Information-theoretically Safe Bias Cla…
Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test…
A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some…
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative…
Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…
We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…
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…
Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…
This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…
Despite the efficiency and scalability of machine learning systems, recent studies have demonstrated that many classification methods, especially deep neural networks (DNNs), are vulnerable to adversarial examples; i.e., examples that are…
Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models.…
Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off…
Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied…
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks. Typical DNN classifiers encode the input image into a compressed latent representation more…
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial…
Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has…
Gradient-based adversarial attacks subtly manipulate inputs of Machine Learning (ML) models to induce incorrect predictions. This paper investigates whether careful architectural choices alone can yield an inherently robust Deep Neural…
Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate…
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…
The idea of robustness is central and critical to modern statistical analysis. However, despite the recent advances of deep neural networks (DNNs), many studies have shown that DNNs are vulnerable to adversarial attacks. Making…