Related papers: Asymptotic Learning Requirements for Stealth Attac…

Statistical dependence between hypotheses poses a significant challenge to the stability of large scale multiple hypotheses testing. Ignoring it often results in an unacceptably large spread in the false positive proportion even though the…

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i.e., sever and clients only hold partial sub-networks and exchange…

We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. The idea is to learn a stochastic representation or encoding of the task description, given by a training set, that…

The effectiveness of Data Injections Attacks (DIAs) critically depends on the completeness of the system information accessible to adversaries. This relationship positions information incompleteness enhancement as a vital defense strategy…

Network-based attacks on control systems may alter sensor data delivered to the controller, effectively causing degradation in control performance. As a result, having access to accurate state estimates, even in the presence of attacks on…

False Data Injection (FDI) attacks against powersystem state estimation are a growing concern for operators.Previously, most works on FDI attacks have been performedunder the assumption of the attacker having full knowledge ofthe underlying…

There are many high dimensional function classes that have fast agnostic learning algorithms when assumptions on the distribution of examples can be made, such as Gaussianity or uniformity over the domain. But how can one be confident that…

This paper studies the problem of remote state estimation in the presence of a passive eavesdropper. A sensor measures a linear plant's state and transmits it to an authorized user over a packet-dropping channel, which is susceptible to…

In recent times we hear increasingly often about cyber attacks on various commercial and strategic sites that manage to escape any defense. In this article, we model such attacks on networks via stochastic processes and predict the time of…

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more…

In this paper, we study the information transmission problem under the distributed learning framework, where each worker node is merely permitted to transmit a $m$-dimensional statistic to improve learning results of the target node.…

This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables…

Cyber data attacks are the worst-case interacting bad data to power system state estimation and cannot be detected by existing bad data detectors. In this paper, we for the first time analyze the likelihood of cyber data attacks by…

The problem of mitigating maliciously injected signals in interconnected systems is dealt with in this paper. We consider the class of covert attacks, as they are stealthy and cannot be detected by conventional means in centralized…

We introduce a stochastic approximation method for the solution of an ergodic Kullback-Leibler control problem. A Kullback-Leibler control problem is a Markov decision process on a finite state space in which the control cost is…

This paper studies the vehicle bicycle model under three classes of stealthy cyber-attacks: replay attacks, zero dynamics attacks, and covert attacks. Using a system-theoretic framework, we analyze the feasibility and impact of these…

We numerically study the two-dimensional, area preserving, web map. When the map is governed by ergodic behavior, it is, as expected, correctly described by Boltzmann-Gibbs statistics, based on the additive entropic functional $S_{BG}[p(x)]…

Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing success of these…

Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a…

Information theoretic measures (e.g. the Kullback Liebler divergence and Shannon mutual information) have been used for exploring possibly nonlinear multivariate dependencies in high dimension. If these dependencies are assumed to follow a…