arXiv subjects

Paul Irofti

Publications and source records attributed to Paul Irofti.

At least 19 recordsLinked to original sources

arXiv2026

Multilingual Coreference Resolution via Cycle-Consistent Machine Translation

Coreference resolution is a core NLP task, having a broad range of downstream applications, e.g.~machine translation, question answering, document summarization, etc. While the task is well-studied in English, comparatively less attention is dedicated to coreference resolution in other languages, especially low-resource ones. To mitigate this gap, we propose a novel coreference resolution pipeline that harnesses machine translation (MT) from English to a target low-resource language, to generate or expand training data. To automatically validate the quality of the translated samples, we back-translate the samples and assess the similarity with the original English samples via cosine similarity in the latent space of a BERT model. The resulting similarity scores are integrated into the loss function to weight training samples according to their MT cycle consistency. Extensive experiments on four low-resource languages show that our pipeline brings significant performance gains in coreference resolution. Moreover, our pipeline enables accurate coreference resolution in languages where no previous corpora were available.

cs.CL↗

arXiv2026

Real-time loosely coupled GNSS and IMU integration via Factor Graph Optimization

Accurate positioning, navigation, and timing (PNT) is fundamental to the operation of modern technologies and a key enabler of autonomous systems. A very important component of PNT is the Global Navigation Satellite System (GNSS) which ensures outdoor positioning. Modern research directions have pushed the performance of GNSS localization to new heights by fusing GNSS measurements with other sensory information, mainly measurements from Inertial Measurement Units (IMU). In this paper, we propose a loosely coupled architecture to integrate GNSS and IMU measurements using a Factor Graph Optimization (FGO) framework. Because the FGO method can be computationally challenging and often used as a post-processing method, our focus is on assessing its localization accuracy and service availability while operating in real-time in challenging environments (urban canyons). Experimental results on the UrbanNav-HK-MediumUrban-1 dataset show that the proposed approach achieves real-time operation and increased service availability compared to batch FGO methods. While this improvement comes at the cost of reduced positioning accuracy, the paper provides a detailed analysis of the trade-offs between accuracy, availability, and computational efficiency that characterize real-time FGO-based GNSS/IMU fusion.

cs.RO↗

arXiv2026

Real-time tightly coupled GNSS and IMU integration via Factor Graph Optimization

Reliable positioning in dense urban environments remains challenging due to frequent GNSS signal blockage, multipath, and rapidly varying satellite geometry. While factor graph optimization (FGO)-based GNSS-IMU fusion has demonstrated strong robustness and accuracy, most formulations remain offline. In this work, we present a real-time tightly coupled GNSS-IMU FGO method that enables causal state estimation via incremental optimization with fixed-lag marginalization, and we evaluate its performance in a highly urbanized GNSS-degraded environment using the UrbanNav dataset.

cs.RO↗

arXiv2026

MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorization

Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalization of zero-shot learning, where the new classes are not known a priori, hence involving the active discovery of new classes. While zero-shot learning has been extensively studied in text classification, especially with the emergence of pre-trained language models, open-set learning and discovery is a comparatively new setup for the text domain. To this end, we introduce the first multilingual open-set learning and discovery (MOSLD) benchmark for text categorization by topic, comprising 960K data samples across 12 languages. To construct the benchmark, we (i) rearrange existing datasets and (ii) collect new data samples from the news domain. Moreover, we propose a novel framework for the OSLD task, which integrates multiple stages to continuously discover and learn new classes. We evaluate several language models, including our own, to obtain results that can be used as reference for future work. We release our benchmark at https://github.com/Adriana19Valentina/MOSLD-Bench.

cs.CL↗

arXiv2026

XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark

Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with many recent studies reporting accuracy rates close to 99%. However, these methods are typically tested in an in-domain setup, where the deepfake samples from the training and test sets are produced by the same generative models. To this end, we introduce XMAD-Bench, a large-scale cross-domain multilingual audio deepfake benchmark comprising 668.8 hours of real and deepfake speech. In our novel dataset, the speakers, the generative methods, and the real audio sources are distinct across training and test splits. This leads to a challenging cross-domain evaluation setup, where audio deepfake detectors can be tested "in the wild". Our in-domain and cross-domain experiments indicate a clear disparity between the in-domain performance of deepfake detectors, which is usually as high as 100%, and the cross-domain performance of the same models, which is sometimes similar to random chance. Our benchmark highlights the need for the development of robust audio deepfake detectors, which maintain their generalization capacity across different languages, speakers, generative methods, and data sources. Our benchmark is publicly released at https://github.com/ristea/xmad-bench/.

cs.SD↗

arXiv2026

Text Classification Under Class Distribution Shift: A Survey

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data changes over time, which hinders the application of conventional ML models. One domain where the distribution shift naturally occurs is text classification, since people always find new topics to discuss. To this end, we survey research articles studying open-set text classification and related tasks. We divide the methods in this area based on the constraints that define the kind of distribution shift and the corresponding problem formulation, i.e. learning with the Universum, zero-shot learning, and open-set learning. We next discuss the predominant mitigation approaches for each problem setup. We further identify several future work directions, aiming to push the boundaries beyond the state of the art. Finally, we explain how continual learning can solve many of the issues caused by the shifting class distribution. We maintain a list of relevant papers at https://github.com/Eduard6421/Open-Set-Survey.

cs.CL↗

arXiv2025

A comparison between joint and dual UKF implementations for state estimation and leak localization in water distribution networks

The sustainability of modern cities highly depends on efficient water distribution management, including effective pressure control and leak detection and localization. Accurate information about the network hydraulic state is therefore essential. This article presents a comparison between two data-driven state estimation methods based on the Unscented Kalman Filter (UKF), fusing pressure, demand and flow data for head and flow estimation. One approach uses a joint state vector with a single estimator, while the other uses a dual-estimator scheme. We analyse their main characteristics, discussing differences, advantages and limitations, and compare them theoretically in terms of accuracy and complexity. Finally, we show several estimation results for the L-TOWN benchmark, allowing to discuss their properties in a real implementation.

eess.SY↗

arXiv2025

Factor Graph Optimization for Leak Localization in Water Distribution Networks

Detecting and localizing leaks in water distribution network systems is an important topic with direct environmental, economic, and social impact. Our paper is the first to explore the use of factor graph optimization techniques for leak localization in water distribution networks, enabling us to perform sensor fusion between pressure and demand sensor readings and to estimate the network's temporal and structural state evolution across all network nodes. The methodology introduces specific water network factors and proposes a new architecture composed of two factor graphs: a leak-free state estimation factor graph and a leak localization factor graph. When a new sensor reading is obtained, unlike Kalman and other interpolation-based methods, which estimate only the current network state, factor graphs update both current and past states. Results on Modena, L-TOWN and synthetic networks show that factor graphs are much faster than nonlinear Kalman-based alternatives such as the UKF, while also providing improvements in localization compared to state-of-the-art estimation-localization approaches. Implementation and benchmarks are available at https://github.com/pirofti/FGLL.

eess.SY↗

arXiv2025

Detecting and Mitigating DDoS Attacks with AI: A Survey

Distributed Denial of Service attacks represent an active cybersecurity research problem. Recent research shifted from static rule-based defenses towards AI-based detection and mitigation. This comprehensive survey covers several key topics. Preeminently, state-of-the-art AI detection methods are discussed. An in-depth taxonomy based on manual expert hierarchies and an AI-generated dendrogram are provided, thus settling DDoS categorization ambiguities. An important discussion on available datasets follows, covering data format options and their role in training AI detection methods together with adversarial training and examples augmentation. Beyond detection, AI based mitigation techniques are surveyed as well. Finally, multiple open research directions are proposed.

cs.CR↗

arXiv2024

Dual Unscented Kalman Filter Architecture for Sensor Fusion in Water Networks Leak Localization

Leakage in water systems results in significant daily water losses, degrading service quality, increasing costs, and aggravating environmental problems. Most leak localization methods rely solely on pressure data, missing valuable information from other sensor types. This article proposes a hydraulic state estimation methodology based on a dual Unscented Kalman Filter (UKF) approach, which enhances the estimation of both nodal hydraulic heads, critical in localization tasks, and pipe flows, useful for operational purposes. The approach enables the fusion of different sensor types, such as pressure, flow and demand meters. The strategy is evaluated in well-known open source case studies, namely Modena and L-TOWN, showing improvements over other state-of-the-art estimation approaches in terms of interpolation accuracy, as well as more precise leak localization performance in L-TOWN.

eess.SY↗

arXiv2024

Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook

We survey deepfake generation and detection techniques, covering all deepfake media types: image, video, audio and multimodal content. We identify various kinds of deepfakes and construct taxonomies of deepfake generation and detection methods, illustrating the important groups of methods. Next, we gather datasets used for deepfake detection and provide updated rankings of the best performing detectors on the most popular datasets. In addition, we develop a novel multimodal benchmark to evaluate deepfake detectors on out-of-distribution content. The results indicate that state-of-the-art detectors fail to generalize to deepfakes generated by unseen generators. Our project page and new benchmark are available at https://github.com/CroitoruAlin/biodeep.

cs.CV↗

arXiv2024

Complexity of Inexact Proximal Point Algorithm for minimizing convex functions with Holderian Growth

Several decades ago the Proximal Point Algorithm (PPA) started to gain a long-lasting attraction for both abstract operator theory and numerical optimization communities. Even in modern applications, researchers still use proximal minimization theory to design scalable algorithms that overcome nonsmoothness. Remarkable works as \cite{Fer:91,Ber:82constrained,Ber:89parallel,Tom:11} established tight relations between the convergence behaviour of PPA and the regularity of the objective function. In this manuscript we derive nonasymptotic iteration complexity of exact and inexact PPA to minimize convex functions under $γ-$Holderian growth: $\BigO{\log(1/ε)}$ (for $γ\in [1,2]$) and $\BigO{1/ε^{γ- 2}}$ (for $γ> 2$). In particular, we recover well-known results on PPA: finite convergence for sharp minima and linear convergence for quadratic growth, even under presence of deterministic noise. Moreover, when a simple Proximal Subgradient Method is recurrently called as an inner routine for computing each IPPA iterate, novel computational complexity bounds are obtained for Restarting Inexact PPA. Our numerical tests show improvements over existing restarting versions of the Subgradient Method.

cs.LG↗

arXiv2024

Fusing Dictionary Learning and Support Vector Machines for Unsupervised Anomaly Detection

We study in this paper the improvement of one-class support vector machines (OC-SVM) through sparse representation techniques for unsupervised anomaly detection. As Dictionary Learning (DL) became recently a common analysis technique that reveals hidden sparse patterns of data, our approach uses this insight to endow unsupervised detection with more control on pattern finding and dimensions. We introduce a new anomaly detection model that unifies the OC-SVM and DL residual functions into a single composite objective, subsequently solved through K-SVD-type iterative algorithms. A closed-form of the alternating K-SVD iteration is explicitly derived for the new composite model and practical implementable schemes are discussed. The standard DL model is adapted for the Dictionary Pair Learning (DPL) context, where the usual sparsity constraints are naturally eliminated. Finally, we extend both objectives to the more general setting that allows the use of kernel functions. The empirical convergence properties of the resulting algorithms are provided and an in-depth analysis of their parametrization is performed while also demonstrating their numerical performance in comparison with existing methods.

cs.LG↗

arXiv2024

Learning Explicitly Conditioned Sparsifying Transforms

Sparsifying transforms became in the last decades widely known tools for finding structured sparse representations of signals in certain transform domains. Despite the popularity of classical transforms such as DCT and Wavelet, learning optimal transforms that guarantee good representations of data into the sparse domain has been recently analyzed in a series of papers. Typically, the conditioning number and representation ability are complementary key features of learning square transforms that may not be explicitly controlled in a given optimization model. Unlike the existing approaches from the literature, in our paper, we consider a new sparsifying transform model that enforces explicit control over the data representation quality and the condition number of the learned transforms. We confirm through numerical experiments that our model presents better numerical behavior than the state-of-the-art.

math.NA↗

arXiv2023

Nodal Hydraulic Head Estimation through Unscented Kalman Filter for Data-driven Leak Localization in Water Networks

In this paper, we present a nodal hydraulic head estimation methodology for water distribution networks (WDN) based on an Unscented Kalman Filter (UKF) scheme with application to leak localization. The UKF refines an initial estimation of the hydraulic state by considering the prediction model, as well as available pressure and demand measurements. To this end, it provides customized prediction and data assimilation steps. Additionally, the method is enhanced by dynamically updating the prediction function weight matrices. Performance testing on the Modena benchmark under realistic conditions demonstrates the method's effectiveness in enhancing state estimation and data-driven leak localization.

eess.SY↗

arXiv2023

Software Mitigation of RISC-V Spectre Attacks

Speculative attacks are still an active threat today that, even if initially focused on the x86 platform, reach across all modern hardware architectures. RISC-V is a newly proposed open instruction set architecture that has seen traction from both the industry and academia in recent years. In this paper we focus on the RISC-V cores where speculation is enabled and, as we show, where Spectre attacks are as effective as on x86. Even though RISC-V hardware mitigations were proposed in the past, they have not yet passed the prototype phase. Instead, we propose low-overhead software mitigations for Spectre-BTI, inspired from those used on the x86 architecture, and for Spectre-RSB, to our knowledge the first such mitigation to be proposed. We show that these mitigations work in practice and that they can be integrated in the LLVM toolchain. For transparency and reproducibility, all our programs and data are made publicly available online.

cs.CR↗

arXiv2023

OpenBSD formal driver verification with SeL4

The seL4 microkernel is currently the only kernel that has been fully formally verified. In general, the increased interest in ensuring the security of a kernel's code results from its important role in the entire operating system. One of the basic features of an operating system is that it abstracts the handling of devices. This abstraction is represented by device drivers - the software that manages the hardware. A proper verification of the software component could ensure that the device would work properly unless there is a hardware failure.In this paper, we choose to model the behavior of a device driver and build the proof that the code implementation matches the expected behavior. The proof was written in Isabelle/HOL, the code translation from C to Isabelle was done automatically by the use of the C-to-Isabelle Parser and AutoCorres tools. We choose Isabelle theorem prover because its efficiency was already shown through the verification of seL4 microkernel.

cs.CR↗

arXiv2023

Pinky: A Modern Malware-oriented Dynamic Information Retrieval Tool

We present here a reverse engineering tool that can be used for information retrieval and anti-malware techniques. Our main contribution is the design and implementation of an instrumentation framework aimed at providing insight on the emulation process. Sample emulation is achieved via translation of the binary code to an intermediate representation followed by compilation and execution. The design makes this a versatile tool that can be used for multiple task such as information retrieval, reverse engineering, debugging, and integration with anti-malware products.

cs.CR↗