There is growing interest in applying graph-based methods to Time Series Anomaly Detection (TSAD), particularly Graph Neural Networks (GNNs), as they naturally model dependencies among multivariate signals. GNNs are typically used as backbones in score-based TSAD pipelines, where anomalies are identified through reconstruction or prediction errors followed by thresholding. However, and despite promising results, the field still lacks standardized frameworks for evaluation and suffers from persistent issues with metric design and interpretation. We thus present an open-source framework for TSAD using GNNs, designed to support reproducible experimentation across datasets, graph structures, and evaluation strategies. Built with flexibility and extensibility in mind, the framework facilitates systematic comparisons between TSAD models and enables in-depth analysis of performance and interpretability. Using this tool, we evaluate several GNN-based architectures alongside baseline models across two real-world datasets with contrasting structural characteristics. Our results show that GNNs not only improve detection performance but also offer significant gains in interpretability, an especially valuable feature for practical diagnosis. We also find that attention-based GNNs offer robustness when graph structure is uncertain or inferred. In addition, we reflect on common evaluation practices in TSAD, showing how certain metrics and thresholding strategies can obscure meaningful comparisons. Overall, this work contributes both practical tools and critical insights to advance the development and evaluation of graph-based TSAD systems.

Network monitoring data generally consists of hundreds of counters periodically collected in the form of time-series, resulting in a complex-to-analyze multivariate time-series (MTS) process. Traditional time-series anomaly detection methods target univariate time-series analysis, which makes the MTS analysis cumbersome and prohibitively complex. We present DC-VAE (Dilated Convolutional -Variational Auto Encoder), a novel approach to anomaly detection in MTS data, leveraging convolutional neural networks (CNNs) and variational autoencoders (VAEs). DC-VAE detects anomalies in MTS data through a single model, exploiting temporal information without sacrificing computational and memory resources. In particular, instead of using recursive neural networks, large causal filters, or many layers, DC-VAE relies on Dilated Convolutions (DC) to capture long and short-term phenomena in the data. We evaluate DC-VAE on the detection of anomalies in the TELCO TELeCOmmunication-networks dataset, a large-scale, multi-dimensional network monitoring dataset collected at an operational mobile Internet Service Provider (ISP), where anomalous events were manually labeled by experts during seven months, at a five-minutes granularity. We benchmark DC-VAE against a broad set of traditional time-series anomaly detectors from the signal processing and machine learning domains. We also evaluate DC-VAE in open, publicly available datasets, comparing its performance against other multivariate anomaly detectors based on deep learning generative models. Results confirm the advantages of DC-VAE, both in terms of MTS data modeling, as well as for anomaly detection. For the sake of reproducibility and as an additional contribution, we make the TELCO dataset publicly available to the community and openly release the code implementing DC-VAE.

We investigate a novel approach to time-series modeling, inspired by the successes of large pre-trained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By Foundation Model (FM), we mean a model pre-trained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling and forecasting on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts and ideas of this FM for time-series (TSFM), and present some preliminary results in a multi-dimensional mobile network monitoring dataset. We also present example results applying novel TSFMs to this dataset, both in a zero-shot manner and relying on fine-tuning, and show how complex it is in the practice to achieve accurate results.

We present a communications-themed Capture the Flag (CTF) tournament, featuring both virtual and in-person formats. In the virtual edition we post online several challenges containing a signal recording and an accompanying story. Registered teams analyze the signal and try to unveil a hidden message, which upon submission earns them points. The in-person variant is a treasure hunt, where hints are provided by signals obtained from any smartphone; e.g. bluetooth or audio. We share pivotal lessons learned in our four years' experience and highlight the role of these recreational activities in fostering community engagement and promoting the dissemination of the discipline.

Network security data generally consists of hundreds of counters periodically collected in the form of time-series, resulting in a complex-to-analyze multivariate time-series (MTS) process. We investigate a novel approach to time-series modeling, inspired by the successes of large pre-trained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pre-trained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. Based on the DC-VAE architecture originally designed for multivariate anomaly detection, FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts and ideas of this foundation model, and present some preliminary results in a multi-dimensional network monitoring dataset, collected from an operational mobile Internet Service Provider (ISP). This work represents a significant step forward in the development of foundation generative-AI models for anomaly detection in time-series analysis, with applications spanning cybersecurity, network management, and beyond.

Multivariate time-series (MTS) play a crucial role in network monitoring and analysis problems. We explore the usage of generative AI for MTS data modeling, in particular for the sake of knowledge replay. Knowledge replay mechanisms help in leveraging past experiences to enhance learning, mitigate forgetting, promote generalization, and enable the transfer of knowledge across different tasks or domains. Using a VAE-based deep architecture for data modeling, we incorporate a Deep Generative Replay (DGR) approach to transfer previously learned latent representations into future learning tasks, enabling continual learning in MTS problems. We study the generative characteristics of VAE-based models on top of a multi-dimensional network monitoring dataset collected from an operational mobile Internet Service Provider (ISP), portraying its usage in the context of DGR learning tasks.

Anomaly detection in Multivariate Time-Series (MTS) data plays an important role in multiple domains, especially in cybersecurity, for the detection of unknown attacks. DC-VAE is a recent approach we have proposed for anomaly detection in network measurement multivariate data, which uses Variational Auto Encoders (VAEs) and Dilated Convolutional Neural Networks (DCNNs) to model complex and high-dimensional MTS data. However, detecting anomalies using VAEs can result in performance degradation and even catastrophic forgetting when trained on dynamic and evolving network measurements, particularly in the event of concept drifts. We extend DC-VAE to a continual learning setup, leveraging the generative AI properties of the underlying models to deal with continually evolving data. We introduce GenDeX, an approach to Generative AI-based anomaly detection which compresses the patterns extracted from past measurements into a generative model that can synthesize MTS data out of input Gaussian noise, mimicking the characteristics of the MTS data used for training. GenDeX relies on a Deep Generative Replay paradigm to realize continual learning, combining synthesized past MTS measurements with new observations to update the detection model. Using a large-scale, multi-dimensional network monitoring dataset collected from an operational mobile Internet Service Provider (ISP), we showcase the functionality of DCVAE in the event of concept drifts, and study in-depth its generative characteristics, assessing GenDeX synthetically generated MTS examples. GenDeX enables DC-VAE adapting to continually evolving data, overcoming the limitations of catastrophic forgetting.

We present DC-VAE, an approach to network anomaly detection in multivariate time-series (MTS), using Variational Auto Encoders (VAEs) and Dilated Convolutional Neural Networks (CNN). DC-VAE detects anomalies in MTS data through a single model, exploiting temporal and spatial MTS information. We showcase DC-VAE in different MTS datasets, and portray its future application in a continual learning framework, exploiting the generative properties of the underlying generative model to deal with continuously evolving data, avoiding catastrophic forgetting. We showcase the functioning of DC-VAE in the event of concept drifts, and propose the application of a novel approach to generative-driven continual learning, introducing the Deep Generative Replay model.

Due to its unsupervised nature, anomaly detection plays a central role in cybersecurity, in particular on the detection of unknown attacks. A major source of cybersecurity data comes in the form of multivariate time-series (MTS), representing the temporal evolution of multiple, usually correlated measurements. Despite the many approaches available in the literature for time-series anomaly detection, the automatic detection of abnormal events in MTS remains a complex problem. In this paper we introduce DC-VAE, a novel approach to anomaly detection in MTS, leveraging convolutional neural networks (CNNs) and variational auto encoders (VAEs). DC-VAE detects anomalies in time-series data, exploiting temporal information without sacrificing computational and memory resources. In particular, instead of using recursive neural networks, large causal filters, or many layers, DC-VAE relies on dilated convolutions (dc) to capture long and short term phenomena in the data, avoiding complex and less-efficient deep architectures, simplifying learning. We evaluate dc-vae on the detection of anoma-lies on a large-scale, multi-dimensional network monitoring dataset collected at an operational mobile internet service provider (isp), where anomalous events were manually labeled during a time span of 7-months, at a five-minutes granularity. Results show the main properties and advantages introduced by VAEs for time-series anomaly detection, as well as the out-performance of dilated convolutions as compared to standard VAEs for time-series modeling.

The topic of indoor localization is very relevant today as it provides solutions in different applications (e.g. shopping malls or museums). We consider here the so-called Wi-Fi fingerprinting approach, where RSSI measurements from the access points are used to locate the device into certain predefined areas. Typically, this mapping from measurements to area is obtained by training a machine learning algorithm. However, traditional techniques do not take into account the underlying geometry of the problem. We thus investigate here a novel approach: using machine learning techniques in graphs, in particular Graph Neural Networks. We propose a way to construct the graph using only the RSSI measurements (and not the floor plan) and evaluate the resulting algorithm on two real datasets. The results are very encouraging, showing a better performance than existing methods, in some cases even using a much smaller amount of training data.

Despite the many attempts and approaches for anomaly de- tection explored over the years, the automatic detection of rare events in data communication networks remains a com- plex problem. In this paper we introduce Net-GAN, a novel approach to network anomaly detection in time-series, us- ing recurrent neural networks (RNNs) and generative ad- versarial networks (GAN). Different from the state of the art, which traditionally focuses on univariate measurements, Net-GAN detects anomalies in multivariate time-series, ex- ploiting temporal dependencies through RNNs. Net-GAN discovers the underlying distribution of the baseline, multi- variate data, without making any assumptions on its nature, offering a powerful approach to detect anomalies in com- plex, difficult to model network monitoring data. We further exploit the concepts behind generative models to conceive Net-VAE, a complementary approach to Net-GAN for net- work anomaly detection, based on variational auto-encoders (VAE). We evaluate Net-GAN and Net-VAE in different monitoring scenarios, including anomaly detection in IoT sensor data, and intrusion detection in network measure- ments. Generative models represent a promising approach for network anomaly detection, especially when considering the complexity and ever-growing number of time-series to monitor in operational networks.

We introduce Net-GAN , a novel approach to network anomaly detection in time-series, using recurrent neural networks (RNNs) and generative adversarial networks (GAN). Different from the state of the art, which traditionally focuses on univariate measurements, Net-GAN detects anomalies in multivariate time-series, exploiting temporal dependencies through RNNs. Net-GAN discovers the underlying distribution of the baseline, multivariate data, without making any assumptions on its nature, offering a powerful approach to detect anomalies in complex, difficult to model network monitoring data. We present preliminary detection results in different monitoring scenarios, including anomaly detection in sensor data, and intrusion detection in network measurements.

Recognition of geometrical shapes in real-time and fully invariant (i.e., invariant under changes in position, scale, and orientation) is a demanding task in automated image analysis. In particular, the generalized Hough transform (GHT) is a well-known algorithm for the recognition of complex patterns out of edge binary images even with disconnected boundaries or corrupted by noise. In this work we present a space multiplexed optical implementation of the GHT which, by exploiting the redundancy derived from multiview sensing of a two-dimensional image and its out- of-focus capture with an adequate pupil array, allows us to obtain in a single shot the GHT of this image invariant to target shift, scale, and orientation. Experimental validation of the working principle is presented, along with an assessment of the robustness of the system against noise in the input.

Anomaly detection is a relevant field of study for many applications and contexts. In this paper we focus in on-line anomaly detection on unidimensional time series provided by different network operator equipments. We have implemented two detection methods, we have optimized them for on-line processing and we have adapted them for integration into a testbed of a well known Hadoop big data platform. We have analyzed the behavior of both methods for the particular datasets available but we also have applied the methods to a publicly available labeled datasets obtaining good results.