Related papers: Illusory Attacks: Information-Theoretic Detectabil…
Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted inputs that are designed…
Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art…
The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathematical justification, to detect adversarial inputs and improve robustness. In this…
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…
Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within…
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…
Adversarial attacks are a potential threat to machine learning models by causing incorrect predictions through imperceptible perturbations to the input data. While these attacks have been extensively studied in unstructured data like…
Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance factor for practical applications. While object detection…
Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…
Autonomous driving systems (ADS) increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign…
The ever-evolving landscape of attacks, coupled with the growing complexity of ICT systems, makes crafting anomaly-based intrusion detectors (ID) and error detectors (ED) a difficult task: they must accurately detect attacks, and they…
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…
In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…
As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data.…
Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…
One of the most interesting application scenarios in anomaly detection is when sequential data are targeted. For example, in a safety-critical environment, it is crucial to have an automatic detection system to screen the streaming data…
Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the computer vision…
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…
The proliferation and application of machine learning based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the…
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching adversarial patches to real objects. However, most of the existing…