Related papers: CheckNet: Secure Inference on Untrusted Devices
For data privacy, system reliability, and security, Blockchain technologies have become more popular in recent years. Despite its usefulness, the blockchain is vulnerable to cyber assaults; for example, in January 2019 a 51% attack on…
In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…
Deep neural networks (DNNs) may outperform human brains in complex tasks, but the lack of transparency in their decision-making processes makes us question whether we could fully trust DNNs with high stakes problems. As DNNs' operations…
We propose distributed deep neural networks (DDNNs) over distributed computing hierarchies, consisting of the cloud, the edge (fog) and end devices. While being able to accommodate inference of a deep neural network (DNN) in the cloud, a…
A rising number of botnet families have been successfully detected using deep learning architectures. While the variety of attacks increases, these architectures should become more robust against attacks. They have been proven to be very…
Network intrusion detection systems (NIDSs) play an important role in computer network security. There are several detection mechanisms where anomaly-based automated detection outperforms others significantly. Amid the sophistication and…
Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent or oversimplified…
Existing uncertainty modeling approaches try to detect an out-of-distribution point from the in-distribution dataset. We extend this argument to detect finer-grained uncertainty that distinguishes between (a). certain points, (b). uncertain…
Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these networks have been shown to often mispredict on inputs with…
Neural networks are vulnerable to adversarial attacks, i.e., small input perturbations can significantly affect the outputs of a neural network. Therefore, to ensure safety of neural networks in safety-critical environments, the robustness…
Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment…
Control Strategies for hierarchical tree-like probabilistic inference networks are formulated and investigated. Strategies that utilize staged look-ahead and temporary focus on subgoals are formalized and refined using the Depth Vector…
The ability of Convolutional Neural Networks (CNNs) to accurately process real-time telemetry has boosted their use in safety-critical and high-performance computing systems. As such systems require high levels of resilience to errors, CNNs…
Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…
The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…
Convolution Neural Network (ConvNet) offers a high potential to generalize input data. It has been widely used in many application areas, such as visual imagery, where comprehensive learning datasets are available and a ConvNet model can be…
Wireless sensor networks (WSNs) have recently attracted a lot of interest in the research community due their wide range of applications. Unfortunately, these networks are vulnerable to numerous security threats that can adversely affect…
Wireless sensor networks (WSNs) have recently attracted a lot of interest in the research community due their wide range of applications. Unfortunately, these networks are vulnerable to numerous security threats that can adversely affect…
Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…
Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to…