Related papers: Probabilistic Jacobian-based Saliency Maps Attacks
Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet…
Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In…
A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…
Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constraint), suitable for interpreting the vulnerability of DNNs.…
Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underexplored. This study systematically evaluates localized adversarial attacks…
In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor…
Machine learning algorithms can effectively classify malware through dynamic behavior but are susceptible to adversarial attacks. Existing attacks, however, often fail to find an effective solution in both the feature and problem spaces.…
While neural ranking models (NRMs) have shown high effectiveness, they remain susceptible to adversarial manipulation. In this work, we introduce Few-Shot Adversarial Prompting (FSAP), a novel black-box attack framework that leverages the…
Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…
In this paper, we study jamming attacks against wireless networks. Specifically, we consider a network of base stations (BS) or access points (AP) and investigate the impact of a fixed number of jammers that are randomly deployed according…
While the robustness of rate-splitting multiple access (RSMA) to imperfect channel state information (CSI) is well-documented, its susceptibility to attacks launched with malicious reconfigurable intelligent surfaces (RISs) remains…
Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes…
Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vulnerability in…
Machine Learning (ML) algorithms have become increasingly popular for supporting Network Intrusion Detection Systems (NIDS). Nevertheless, extensive research has shown their vulnerability to adversarial attacks, which involve subtle…
Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet…
Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…
Neural networks are frequently used for image classification, but can be vulnerable to misclassification caused by adversarial images. Attempts to make neural network image classification more robust have included variations on…
The burgeoning fields of machine learning (ML) and quantum machine learning (QML) have shown remarkable potential in tackling complex problems across various domains. However, their susceptibility to adversarial attacks raises concerns when…
Non-orthogonal multiple access (NOMA) is a promising technology to increase the spectral efficiency and enable massive connectivity in 5G and future wireless networks. In contrast to orthogonal schemes, such as OFDMA, NOMA multiplexes…
Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the…