Related papers: Analytical Study of Adversarial Strategies in Clus…

Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial…

Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated…

This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial…

Motivated, in part, by the rise of permissionless systems such as Bitcoin where arbitrary nodes (whose identities are not known apriori) can join and leave at will, we extend established research in scalable Byzantine agreement to a more…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

We study the vulnerability of dominating sets against random and targeted node removals in complex networks. While small, cost-efficient dominating sets play a significant role in controllability and observability of these networks, a fixed…

Byzantine robustness has received significant attention recently given its importance for distributed and federated learning. In spite of this, we identify severe flaws in existing algorithms even when the data across the participants is…

This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We…

This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that…

Overlay networks present an interesting challenge for fault-tolerant computing. Many overlay networks operate in dynamic environments (e.g. the Internet), where faults are frequent and widespread, and the number of processes in a system may…

We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We seek to design strategies for the learner to successfully interact with the opponent. While most previous…

The ordered transmission (OT) scheme reduces the number of transmissions needed in the network to make the final decision, while it maintains the same probability of error as the system without using OT scheme. In this paper, we investigate…

\textit{When an adversary gets access to the data sample in the adversarial robustness models and can make data-dependent changes, how has the decision maker consequently, relying deeply upon the adversarially-modified data, to make…

Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome.…

Machine learning has been widely applied in wireless communications. However, the security aspects of machine learning in wireless applications have not been well understood yet. We consider the case that a cognitive transmitter senses the…

We study network games in which players choose both the partners with whom they associate and an action level (e.g., effort) that creates spillovers for those partners. We introduce a framework and two solution concepts, extending standard…

With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the…

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…

In this paper, we propose an algorithm that targets contamination and eavesdropping adversaries. We consider the case when the number of independent packets available to the eavesdropper is less than the multicast capacity of the network.…

Detecting and handling network partitions is a fundamental requirement of distributed systems. Although existing partition detection methods in arbitrary graphs tolerate unreliable networks, they either assume that all nodes are correct or…