Related papers: DeepLaser: Practical Fault Attack on Deep Neural N…
Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…
With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse…
Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making. Despite their transforming impact, DNNs face…
Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge…
Intrusion detection into computer networks has become one of the most important issues in cybersecurity. Attackers keep on researching and coding to discover new vulnerabilities to penetrate information security system. In consequence…
The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance. In this paper we introduce a large taxonomy of faults in deep learning (DL) systems.…
A growing demand is witnessed in both industry and academia for employing Deep Learning (DL) in various domains to solve real-world problems. Deep Reinforcement Learning (DRL) is the application of DL in the domain of Reinforcement Learning…
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…
Nowadays, we are witnessing an increasing effort to improve the performance and trustworthiness of Deep Neural Networks (DNNs), with the aim to enable their adoption in safety critical systems such as self-driving cars. Multiple testing…
Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks. In this paper, we focus on the so-called \textit{backdoor attack},…
Due to the widespread application of deep neural networks~(DNNs) in safety-critical tasks, deep learning testing has drawn increasing attention. During the testing process, test cases that have been fuzzed or selected using test metrics are…
In recent years, deep learning has shown itself to be an incredibly valuable tool in cybersecurity as it helps network intrusion detection systems to classify attacks and detect new ones. Adversarial learning is the process of utilizing…
The functionality of electronic circuits can be seriously impaired by the occurrence of dynamic hardware faults. Particularly, for digital ultra low-power systems, a reduced safety margin can increase the probability of dynamic failures.…
Due to their proven efficiency, machine-learning systems are deployed in a wide range of complex real-life problems. More specifically, Spiking Neural Networks (SNNs) emerged as a promising solution to the accuracy, resource-utilization,…
The popularity of Software Defined Networks (SDNs) has grown in recent years, mainly because of their ability to simplify network management and improve network flexibility. However, this also makes them vulnerable to various types of cyber…
We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions. While DNNs have empirically shown higher performance than…
Deep neural networks (DNNs) have become increasingly popular in recent years. However, despite their many successes, DNNs may also err and produce incorrect and potentially fatal outputs in safety-critical settings, such as autonomous…
The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…
We propose HASHTAG, the first framework that enables high-accuracy detection of fault-injection attacks on Deep Neural Networks (DNNs) with provable bounds on detection performance. Recent literature in fault-injection attacks shows the…
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its…