Online Meta-Learning
A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch. In contrast, online (regret based) learning considers a sequential setting in which problems are revealed one after the other, but conventionally train only a single model without any task-specific adaptation. This work introduces an online meta-learning setting, which merges ideas from both the aforementioned paradigms to better capture the spirit and practice of continual lifelong learning. We propose the follow the meta leader algorithm which extends the MAML algorithm to this setting. Theoretically, this work provides an $\mathcal{O}(\log T)$ regret guarantee with only one additional higher order smoothness assumption in comparison to the standard online setting. Our experimental evaluation on three different large-scale tasks suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches. …

Rank-one Multi-Reference Factor Analysis
In recent years, there is a growing need for processing methods aimed at extracting useful information from large datasets. In many cases the challenge is to discover a low-dimensional structure in the data, often concealed by the existence of nuisance parameters and noise. Motivated by such challenges, we consider the problem of estimating a signal from its scaled, cyclically-shifted and noisy observations. We focus on the particularly challenging regime of low signal-to-noise ratio (SNR), where different observations cannot be shift-aligned. We show that an accurate estimation of the signal from its noisy observations is possible, and derive a procedure which is proved to consistently estimate the signal. The asymptotic sample complexity (the number of observations required to recover the signal) of the procedure is $1/\operatorname{SNR}^4$. Additionally, we propose a procedure which is experimentally shown to improve the sample complexity by a factor equal to the signal’s length. Finally, we present numerical experiments which demonstrate the performance of our algorithms, and corroborate our theoretical findings. …

Attack Graph Obfuscation
Before executing an attack, adversaries usually explore the victim’s network in an attempt to infer the network topology and identify vulnerabilities in the victim’s servers and personal computers. Falsifying the information collected by the adversary post penetration may significantly slower lateral movement and increase the amount of noise generated within the victim’s network. We investigate the effect of fake vulnerabilities within a real enterprise network on the attacker performance. We use the attack graphs to model the path of an attacker making its way towards a target in a given network. We use combinatorial optimization in order to find the optimal assignments of fake vulnerabilities. We demonstrate the feasibility of our deception-based defense by presenting results of experiments with a large scale real network. We show that adding fake vulnerabilities forces the adversary to invest a significant amount of effort, in terms of time and exploitability cost. …

Adaptive Sznajd Model
Understanding the way in which human opinion changes along time and space constitutes one of the great challenges in complex systems research. Among the several approaches that have been attempted at studying this problem, the Sznajd model provides some particularly interesting features, such as its simplicity and ability to represent some of the mechanisms believed to be involved in opinion dynamics. The standard Sznajd model at zero temperature is characterized by converging to one stable state, implying null diversity of opinions. In the present work, we develop an approach — namely the adaptive Sznajd model — in which changes of opinion by an individual (i.e. a network node) implies in possible alterations in the network topology. This is accomplished by allowing agents to change their connections preferentially to other neighbors with the same state. The diversity of opinions along time is quantified in terms of the exponential of the entropy of the opinions density. Several interesting results are reported, including the possible formation of echo chambers or social bubbles. Also, depending on the parameters configuration, the dynamics may converge to different equilibrium states for the same parameter setting. We also investigate the dynamics of the proposed adaptive model at non-null temperatures. …