Network intrusion detection remains a critical challenge in cybersecurity. While supervised machine learning models achieve state-of-the-art performance, their reliance on large labelled datasets makes them impractical for many real-world applications. Anomaly detection methods, which train exclusively on benign traffic to identify malicious activity, suffer from high false positive rates, limiting their usability. Recently, self-supervised learning techniques have demonstrated improved performance with lower false positive rates by learning discriminative latent representations of benign traffic. In particular, contrastive self-supervised models achieve this by minimizing the distance between similar (positive) views of benign traffic while maximizing it between dissimilar (negative) views. Existing approaches generate positive views through data augmentation and treat other samples as negative. In contrast, this work introduces Contrastive Learning using Augmented Negative pairs (CLAN), a novel paradigm for network intrusion detection where augmented samples are treated as negative views - representing potentially malicious distributions - while other benign samples serve as positive views. This approach enhances both classification accuracy and inference efficiency after pretraining on benign traffic. Experimental evaluation on the Lycos2017 dataset demonstrates that the proposed method surpasses existing self-supervised and anomaly detection techniques in a binary classification task. Furthermore, when fine-tuned on a limited labelled dataset, the proposed approach achieves superior multi-class classification performance compared to existing self-supervised models.

In this article, we present a novel information access approach inspired by the information foraging theory (IFT) and elephant herding optimization (EHO). First, we propose a model for information access on social media based on the IFT. We then elaborate an adaptation of the original EHO algorithm to apply it to the information access problem. The combination of the IFT and EHO constitutes a good opportunity to find relevant information on social media. However, when dealing with voluminous data, the performance undergoes a sharp drop. To overcome this issue, we developed an enhanced version of EHO for large scale information access. We introduce new operators to the algorithm, including territories delimitation and clan migration using clustering. To validate our work, we created a dataset of more than 1.4 million tweets, on which we carried out extensive experiments. The outcomes reveal the ability of our approach to find relevant information in an effective and efficient way. They also highlight the advantages of the improved version of EHO over the original algorithm regarding different aspects. Furthermore, we undertook a comparative study with two other metaheuristic-based information foraging approaches, namely ant colony system and particle swarm optimization. Overall, the results are very promising.

In ambient assisted living, human activity recognition from time series sensor data mainly focuses on predefined activities, often overlooking new activity patterns. We propose CLAN, a two-tower contrastive learning-based novelty detection framework with diverse types of negative pairs for human activity recognition. It is tailored to challenges with human activity characteristics, including the significance of temporal and frequency features, complex activity dynamics, shared features across activities, and sensor modality variations. The framework aims to construct invariant representations of known activity robust to the challenges. To generate suitable negative pairs, it selects data augmentation methods according to the temporal and frequency characteristics of each dataset. It derives the key representations against meaningless dynamics by contrastive and classification losses-based representation learning and score function-based novelty detection that accommodate dynamic numbers of the different types of augmented samples. The proposed two-tower model extracts the representations in terms of time and frequency, mutually enhancing expressiveness for distinguishing between new and known activities, even when they share common features. Experiments on four real-world human activity datasets show that CLAN surpasses the best performance of existing novelty detection methods, improving by 8.3%, 13.7%, and 53.3% in AUROC, balanced accuracy, and FPR@TPR0.95 metrics respectively.

Redistribution of resources within a group as a method to reduce wealth inequality is a current area of debate. The evolutionary path to or away from wealth sharing is also a subject of active research. In order to investigate effects and evolution of wealth sharing, societies are simulated using a minimal model of a complex adapting system. These simulations demonstrate, for this artificial foraging society, that local sharing of resources reduces the economy's total wealth and increases wealth inequality. Evolutionary pressures strongly select against local sharing, whether globally or within a individual's clan, and select for asocial behaviors. By holding constant the gene for sharing resources among neighbors, from rich to poor, either with everyone or only within members of the same clan, social behavior is selected but total wealth and mean age are substantially reduced relative to non-sharing societies. The Gini coefficient is shown to be ineffective in measuring these changes in total wealth and wealth distributions, and, therefore, individual well-being. Only with sociality do strategies emerge that allow sharing clans to exclude or coexist with non-sharing clans. These strategies are based on spatial effects, emphasizing the importance of modeling movement mediated community assembly and coexistence as well as sociality.

ABSTRACT In this paper, a new swarm intelligence algorithm based on orca behaviors is proposed for problem solving. The algorithm called artificial orca algorithm (AOA) consists of simulating the orca lifestyle and in particular the social organization, the echolocation mechanism, and some hunting techniques. The originality of the proposal is that for the first time a meta-heuristic simulates simultaneously several behaviors of just one animal species. AOA was adapted to discrete problems and applied on the maze game with four level of complexity. A bunch of substantial experiments were undertaken to set the algorithm parameters for this issue. The algorithm performance was assessed by considering the success rate, the run time, and the solution path size. Finally, for comparison purposes, the authors conducted a set of experiments on state-of-the-art evolutionary algorithms, namely ACO, BA, BSO, EHO, PSO, and WOA. The overall obtained results clearly show the superiority of AOA over the other tested algorithms. INTRODUCTION AND MOTIVATION Based on the No Free Lunch Theorem (Adam & Alexandropoulos, 2019), a swarm intelligence algorithm integrating several important behaviors from animal intelligence was designed.

Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training. However, there is little understanding of applying gradient compression to adaptive gradient methods. Moreover, its performance benefits are often limited by the non-negligible compression overhead. In this paper, we first introduce a novel adaptive gradient method with gradient compression. We show that the proposed method has a convergence rate of $\mathcal{O}(1/\sqrt{T})$ for non-convex problems. In addition, we develop a scalable system called BytePS-Compress for two-way compression, where the gradients are compressed in both directions between workers and parameter servers. BytePS-Compress pipelines the compression and decompression on CPUs and achieves a high degree of parallelism. Empirical evaluations show that we improve the training time of ResNet50, VGG16, and BERT-base by 5.0%, 58.1%, 23.3%, respectively, without any accuracy loss with 25 Gb/s networking. Furthermore, for training the BERT models, we achieve a compression rate of 333x compared to the mixed-precision training.

Modeling the distribution of high dimensional data by a latent tree graphical model is a common approach in multiple scientific domains. A common task is to infer the underlying tree structure given only observations of the terminal nodes. Many algorithms for tree recovery are computationally intensive, which limits their applicability to trees of moderate size. For large trees, a common approach, termed divide-and-conquer, is to recover the tree structure in two steps. First, recover the structure separately for multiple randomly selected subsets of the terminal nodes. Second, merge the resulting subtrees to form a full tree. Here, we develop Spectral Top-Down Recovery (STDR), a divide-and-conquer approach for inference of large latent tree models. Unlike previous methods, STDR's partitioning step is non-random. Instead, it is based on the Fiedler vector of a suitable Laplacian matrix related to the observed nodes. We prove that under certain conditions this partitioning is consistent with the tree structure. This, in turn leads to a significantly simpler merging procedure of the small subtrees. We prove that STDR is statistically consistent, and bound the number of samples required to accurately recover the tree with high probability. Using simulated data from several common tree models in phylogenetics, we demonstrate that STDR has a significant advantage in terms of runtime, with improved or similar accuracy.

It's been a wild ride this year, but you can always rely on Assassin's Creed to lighten the mood. Let's see what those zany historians at Ubisoft have cooked up for us in the excitingly named Assassin's Creed Valhalla … Peterborough, is it? I have nothing against our beautiful cathedral cities, rolling plains and park-and-ride services, but after 12 months of Brexit, Covid-19 and forest fires, plus the cancellation of the Eurovision song contest, I was hoping for something a little less Tough Mudder from this giddy, quasi-historical, action-adventure series, which previously had us gallivanting around Atlantis. For the first few hours, you're thrown into the icy political drama of ninth-century Norway, where Viking warrior Eivor runs around snow-blasted islands having stern conversations about the future of her clan. I went with female Eivor.)

After a day-long Photoshop teaser and a cinematic trailer, we finally got to see Ubisoft's new Assassin's Creed game in action. During Microsoft's recent Inside Xbox stream, the company showed off gameplay footage of Assassin's Creed Valhalla. The trailer had a bit of everything. We got to see Eivor, the game's protagonist, lead an attack on a castle as well as sail a longboat. The trailer also offered a variety of vistas to see, with England's historic Stonehenge making an appearance at one point.

Following yesterday's Photoshop teaser, Ubisoft has shared the first cinematic trailer for Assassin's Creed Valhalla. When the game comes out this holiday season, you'll be able to play it on both current-generation -- PlayStation 4 and Xbox One -- and next-generation consoles -- Xbox Series X and PlayStation 5 -- as well as Windows PC and Google Stadia. In Assassin's Creed Valhalla, the player will assume the role of Eivor, the leader of a Viking clan. You'll be able to play as either a male or female Eivor. What's more, you'll have the ability to customize your character's hair, tattoos and war paint.