arXiv subjects
Publications and source records attributed to M. Andrecut.
We discuss a class of cellular automata (CA) able to produce long random strings, starting from short "seed" strings. The approach uses two principles borrowed from cryptography: diffusion and confusion. We show numerically that the strings are pseudo-random using three approaches based on: Fourier transform, entropy estimation, and compression. An application to cryptography is also included with the corresponding Python code.
In this paper we discuss several surprisingly simple methods for transforming the Raspberry Pi Pico (RP2) microcontroller into a radio transmitter, by using only cheap off the shelf electronic components, and open source software. While initially this transformation may look as a harmless curiosity, in some extreme cases it can also pose security risks, since it can be used to open a large number of local stealth radio communication channels.
Populations of agents often exhibit surprising collective behavior emerging from simple local interactions. The common belief is that the agents must posses a certain level of cognitive abilities for such an emerging collective behavior to occur. However, contrary to this assumption, it is also well known that even noncognitive agents are capable of displaying nontrivial behavior. Here we consider an intermediate case, where the agents borrow a little bit from both extremes. We assume a population of agents performing random-walk in a bounded environment, on a square lattice. The agents can sense their immediate neighborhood, and they will attempt to move into a randomly selected empty site, by avoiding collisions.Also, the agents will temporary stop moving when they are in contact with at least two other agents. We show that surprisingly, such a rudimentary population of agents undergoes a percolation phase transition and self-organizes in a large polymer like structure, as a consequence of an attractive entropic force emerging from their restricted-valence and local spatial arrangement.
The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A general assumption is that these networks require a large number of hidden neurons relative to the dimensionality of the data samples, in order to achieve good classification accuracy. Contrary to this assumption, here we show that one can obtain good classification results even if the number of hidden neurons has the same order of magnitude as the dimensionality of the data samples, if this dimensionality is reasonably high. Inspired by this result, we also develop an efficient iterative residual training method for such random neural networks, and we extend the algorithm to the least-squares kernel version of the neural network model. Moreover, we also describe an encryption (obfuscation) method which can be used to protect both the data and the resulted network model.
Elections play a fundamental role in democratic societies, however they are often characterized by unexpected results. Here we discuss an election campaign model inspired by the compartmental epidemiology, and we show that the model captures the main characteristics of an election campaign: persuasion, betrayal and regret. All of these three factors can be used together or independently to influence the campaign, and to determine the winner. We include results for both the deterministic and the stochastic versions of the model, and we show that the decision to not vote significantly increases the fluctuations in the model, amplifying the chance of controversial results, in agreement with the well known "paradox of not voting".
Optimal transport aims to learn a mapping of sources to targets by minimizing the cost, which is typically defined as a function of distance. The solution to this problem consists of straight line segments optimally connecting sources to targets, and it does not exhibit branching. These optimal solutions are in stark contrast with both natural, and man-made transportation networks, where branching structures are prevalent. Here we discuss a fast heuristic branching method for optimal transport in networks. We also provide several numerical applications to synthetic examples, a simplified cardiovascular network, and the "Santa Claus" distribution network which includes 141,182 cities around the world, with known location and population.
We discuss a boosting approach for the Ridge Regression (RR) method, with applications to the Extreme Learning Machine (ELM), and we show that the proposed method significantly improves the classification performance and robustness of ELMs.
Predicting the dynamics of chaotic systems is one of the most challenging tasks for neural networks, and machine learning in general. Here we aim to predict the spatiotemporal chaotic dynamics of a high-dimensional non-linear system. In our attempt we use the TensorFlow library, representing the state of the art for deep neural networks training and prediction. While our results are encouraging, and show that the dynamics of the considered system can be predicted for short time, we also indirectly discovered an unexpected and undesirable behavior of the TensorFlow library. More specifically, the longer term prediction of the system's chaotic behavior quickly deteriorates and blows up due to the nondeterministic behavior of the TensorFlow library. Here we provide numerical evidence of the short time prediction ability, and of the longer term predictability blow up.
The recently introduced Theory of the Adjacent Possible (TAP) is a model of combinatorial innovation aiming to explain the "hockey-stick" upward trend of human technological evolution, where an explosion in the number of produced items with increasing complexity suddenly occurs. In addition, the TAP model was also used to explain the rapidly emerging biological complexity. Inspired by TAP here we propose a reaction-diffusion system aiming to extend the model in both space and time. We show that the new model exhibits similar characteristics to the TAP model, like the sudden increase in the production of items, after a longer period of slow growth. The new model also exhibits wave propagation of "innovation", resulting in self-sustained complex interference patterns.
We discuss a simple approach to transform autoencoders into "pattern filters". Besides filtering, we show how this simple approach can be used also to build robust classifiers, by learning to filter only patterns of a given class.
We propose an adaptive threshold multi secret sharing scheme based solely on cryptographically secure hash functions. We show that the proposed scheme is also: perfect, ideal, verifiable, and proactive. Moreover the proposed scheme has a low computational complexity comparing to the most common schemes operating over finite fields.
Intrusion detection systems (IDS) are used to monitor networks or systems for attack activity or policy violations. Such a system should be able to successfully identify anomalous deviations from normal traffic behavior. Here we discuss the machine learning approach to building an anomaly-based IDS using the CSE-CIC-IDS2018 dataset. Since the publication of this dataset a relatively large number of papers have been published, most of them presenting IDS architectures and results based on complex machine learning methods, like deep neural networks, gradient boosting classifiers, or hidden Markov models. Here we show that similar results can be obtained using a very simple nearest neighbor classification approach, avoiding the inherent complications of training such complex models. The advantages of the nearest neighbor algorithm are: (1) it is very simple to implement; (2) it is extremely robust; (3) it has no parameters, and therefore it cannot overfit the data. This result also shows that currently there is a trend of developing over-engineered solutions in the machine learning community. Such solutions are based on complex methods, like deep learning neural networks, without even considering baseline solutions corresponding to simple, but efficient methods.
Behavioral Indicators of Compromise are associated with various automated methods used to extract the sample behavior by observing the system function calls performed in a virtual execution environment. Thus, every sample is described by a set of BICs triggered by the sample behavior in the sandbox environment. Here we discuss a Machine Learning approach to the classification of the sandbox samples as MALICIOUS or BENIGN, based on the list of triggered BICs. Besides the more traditional methods like Logistic Regression and Naive Bayes Classification we also discuss a different approach inspired by the statistical Monte Carlo methods. The numerical results are illustrated using ThreatGRID and ReversingLabs data.
We discuss a diffusion based implementation of the self-organizing map on the unit hypersphere. We show that this approach can be efficiently implemented using just linear algebra methods, we give a python numpy implementation, and we illustrate the approach using the well known MNIST dataset.
The hashing trick is a machine learning technique used to encode categorical features into a numerical vector representation of pre-defined fixed length. It works by using the categorical hash values as vector indices, and updating the vector values at those indices. Here we discuss a different approach based on additive-hashing and the "almost orthogonal" property of high-dimensional random vectors. That is, we show that additive feature hashing can be performed directly by adding the hash values and converting them into high-dimensional numerical vectors. We show that the performance of additive feature hashing is similar to the hashing trick, and we illustrate the results numerically using synthetic, language recognition, and SMS spam detection data.
We combine K-means clustering with the least-squares kernel classification method. K-means clustering is used to extract a set of representative vectors for each class. The least-squares kernel method uses these representative vectors as a training set for the classification task. We show that this combination of unsupervised and supervised learning algorithms performs very well, and we illustrate this approach using the MNIST dataset
Here we discuss a new fast detrending method for the non-stationary RR time series used in Heart Rate Variability analysis. The described method is based on the diffusion equation, and we show numerically that it is equivalent to the widely used Smoothing Priors Approach (SPA) and Wavelet Smoothing Approach (WSA) methods. The speed of the proposed method is comparable to the WSA method and it is several orders of magnitude faster than the SPA method, which makes it suitable for very long time series analysis.
In this paper we explore the "vector semantics" problem from the perspective of "almost orthogonal" property of high-dimensional random vectors. We show that this intriguing property can be used to "memorize" random vectors by simply adding them, and we provide an efficient probabilistic solution to the set membership problem. Also, we discuss several applications to word context vector embeddings, document sentences similarity, and spam filtering.