The new study, published in the journal Multimedia Tools and Applications, addresses a task known as text-independent offline writer identification. Offline means the system works from static images of handwriting — photographs or scans of paper documents — rather than from digital pen strokes captured in real time. Text-independent means the system cannot rely on recognizing specific words or characters: it must judge authorship from style alone, even when the documents being compared contain entirely different content. This is by far the harder version of the problem, and it is the version that matters most in practice, because forensic investigators, archivists, and historians rarely get to choose what text a writer happened to leave behind.

The difficulty stems from the sheer variability of human handwriting. The authors of the study point out that a person’s script shifts with age, education, emotional state, and even the intention behind the writing, while the appearance of a scanned document is further distorted by the writing instrument used and the conditions of acquisition. A ballpoint pen on glossy paper produces a different image than a fountain pen on rough fiber, even when the same hand guides both. Any system that hopes to identify writers reliably must therefore extract features that are stable across all of these nuisance factors while remaining sensitive to the deep, persistent individuality of motor habits.

The core of the proposed framework is a modified vision transformer built around what the researchers call local-global attention blocks. In a conventional vision transformer, an image is chopped into small patches, and a self-attention mechanism lets every patch exchange information with every other patch through learned projections known as queries, keys, and values. This global attention is powerful, but it has a weakness for handwriting: the most telling stylistic evidence often lives in fine local structures — the curve of a single stroke, the junction where two lines meet — and standard projection layers can blur or wash out those details. The team’s solution is to replace the standard query, key, and value projections with depth-wise separable convolutional projections, a lightweight convolutional operation that processes each channel of the patch representation independently before combining them. The effect is that the network preserves local handwriting structures while still allowing patches to communicate across the whole page.

The second innovation is a global average pooling branch woven into the architecture through a gated skip connection. Pooling across the entire feature map gives the network a compressed summary of the page’s overall writing style — spacing, rhythm, and layout tendencies that no single patch can convey. The gate, a learned switch, lets the model decide dynamically how much of this global context to blend into the local features at each block. The result is an architecture that simultaneously attends to the microscopic texture of strokes and the macroscopic character of the page, mirroring the way a human examiner might zoom in on a suspicious letterform and then step back to judge the overall flow of the script.

Getting the input right is half the battle, and the researchers designed a careful preprocessing pipeline to feed their network. Scanned pages are first segmented into individual text lines, and then words are recombined into coherent patch inputs. This matters because handwriting does not respect neat rectangular boundaries: ascenders and descenders from adjacent lines can overlap, and word spacing varies wildly between writers. By reconstructing word-level regions after line segmentation, the framework gives the transformer patches that correspond to meaningful units of writing rather than arbitrary crops, so the attention mechanism operates on fragments that actually carry stylistic information.

At the matching stage, the system condenses each document into a 512-dimensional feature representation — a numerical fingerprint of writing style — and performs page-level writer matching against a reference database. Page-level matching is a deliberate design choice. Earlier systems often compared documents line by line and then aggregated the results, but the authors show that their page-level strategy improves Top-1 accuracy, meaning the correct writer appears at the very top of the ranked candidate list more often. Intuitively, a full page offers a richer and more redundant sample of a writer’s habits than any single line, and the local-global attention architecture is precisely what allows the network to exploit that abundance without drowning in it.

The experimental evidence comes from three widely used benchmark datasets: IAM, CVL, and Firemaker. These collections span different languages, scripts, and acquisition conditions, which makes them a demanding test of generalization. IAM, drawn from English sentences copied by hundreds of writers, tests performance on unconstrained modern script. CVL concentrates on single-page samples from a large writer pool, stressing the system’s ability to discriminate when it has only limited material per person. Firemaker adds further variety in writing styles and document conditions. Across all three, the proposed framework achieved strong identification performance and consistently outperformed the line-level matching strategy, supporting the authors’ argument that page-level reasoning combined with local-global attention is the right recipe for the task.

The significance of this work extends beyond a leaderboard result. Writer identification sits at the intersection of biometrics, forensics, and cultural heritage. In forensic contexts, a robust text-independent system could help narrow suspect lists from questioned documents. In archives and libraries, it could assist in attributing unsigned manuscripts, detecting forgeries within historical collections, and tracing the hands behind medieval scripts — an application area where deep learning for writer identification has already shown promise. The architectural idea at the heart of the study, blending convolutional inductive biases into transformer attention, also reflects a broader trend in computer vision, echoing hybrid designs explored in models such as LeViT, Swin Transformer, and RegionViT, which similarly reconsider where pure global attention helps and where local structure must be protected.

There are, of course, limits to what the published results establish. The study reports performance on benchmark datasets rather than on casework material, and real forensic documents introduce degradations — folds, stains, partial pages, mixed writers — that benchmarks only approximate. Handwriting also changes over a person’s lifetime, and the authors themselves enumerate the subjective and objective factors that make the problem hard. Still, the framework’s design choices are well motivated and its evaluation spans three independent datasets, which lends credibility to the central claim: that depth-wise separable convolutional projections and gated global context give transformers the sensitivity handwriting demands. As handwriting analysis joins the growing list of domains being reshaped by attention-based models, this study offers a concrete demonstration that the architecture of the AI era can be tuned to one of humanity’s oldest biometric traits — the way each of us, uniquely, puts pen to paper.

Subject of Research: Text-independent offline writer identification using a transformer with local-global attention blocks

Article Title: Text-Independent Offline Writer Identification with Local–Global Transformer Attention

Article References: Ri, C.-Y., Choe, K.-H., Ri, M.-G., Choe, H.-S., & Ri, S.-J. (2026). Text-Independent Offline Writer Identification with Local–Global Transformer Attention. Multimedia Tools and Applications, 85(10), Article 797. https://doi.org/10.1007/s11042-026-21932-0

Image Credits: AI Generated

DOI: 10.1007/s11042-026-21932-0

Keywords: writer identification, handwriting analysis, transformer, vision transformer, self-attention, biometrics, forensics, deep learning, computer vision, IAM dataset, pattern recognition, local-global attention

The core problem the researchers set out to solve is architectural. Traditional intrusion detection systems for vehicle networks tend to be centralized: raw data from thousands of vehicles is funneled to a central server, where a machine learning model scans it for signs of malicious activity. That design creates several weaknesses at once. It introduces communication bottlenecks and latency, which are dangerous when a response to an attack must happen in milliseconds. It concentrates critical vehicle data in one place, creating an attractive target for attackers and raising privacy concerns. And it produces a single point of failure: if the central detector is compromised or overwhelmed, the entire fleet loses its protective umbrella. As IoV deployments scale into the millions of vehicles, these limitations become untenable.

IoV BCFL+ inverts that architecture using federated learning, a technique in which the detection model is trained locally on each participating vehicle or edge node, and only the learned model updates, not the raw data, are shared for aggregation. This preserves privacy by keeping driving records, communication logs, and behavioral traces on the vehicles themselves. But federated learning brings its own vulnerabilities. If some participants are malicious or compromised, they can poison the shared model by submitting corrupted updates, a scenario known as a model poisoning attack. The framework addresses this with what the authors call Blockchain Anchored Trust Weighted Federated Aggregation, in which each participant’s contributions are weighted by a trust score, and the aggregation process is anchored to a blockchain so that the history of model updates cannot be silently altered.

The blockchain component is not a generic ledger bolted on for publicity. The researchers use a Proof of Authority consensus mechanism, which is far lighter than the energy-hungry Proof of Work schemes behind cryptocurrencies and therefore better suited to the tight computational and latency budgets of vehicular networks. Smart contracts encoded on the chain enforce what the authors describe as consensus-driven, self-evolving model governance: rules for how the detection model is updated, how trust scores rise and fall, and how misbehaving nodes are handled are executed automatically rather than managed by a central administrator. The governance layer is designed to evolve over time, adjusting to new attack patterns and network conditions rather than remaining a static set of policies.

Detection itself relies on a mobility-aware spatio-temporal representation module. Vehicles in traffic are inherently dynamic objects: their communication patterns change with speed, density, road topology, and time of day. A static classifier trained on fixed network snapshots will miss attacks that only reveal themselves in the temporal evolution of vehicle behavior. The framework builds representations that capture both spatial relationships among vehicles, such as which nodes are communicating with which neighbors, and temporal dynamics, such as how those relationships shift across successive time windows. This is the kind of pattern recognition where recurrent and attention-based deep learning architectures excel, and the authors situate their approach within a body of prior work using BiLSTM networks, graph transformers, and spatio-temporal attention models for network intrusion detection.

One of the more distinctive elements of the study is its treatment of forensic evidence. When an intrusion is detected, investigators need trustworthy records of what happened, but storing bulky evidence on-chain would be slow and expensive. IoV BCFL+ adopts a hybrid on-chain and off-chain structure: cryptographic fingerprints and metadata of intrusion evidence are anchored on the blockchain, while the full evidence payloads are stored off-chain on the InterPlanetary File System, a distributed storage network. This design pays off in a striking way in the reported results: forensic retrieval time was reduced by more than 40 percent compared with conventional approaches, meaning that incident response teams can reconstruct an attack timeline substantially faster. Security of the evidence pipeline is reinforced with lightweight cryptographic measures, including dynamic key management and the ASCON authenticated encryption cipher, which is designed for resource-constrained devices.

Anticipating that attackers will not stand still, the authors also built adversarial stress testing into the development cycle. Through what they call Federated Adversarial Scenario Stress Testing, the detection model is deliberately challenged with adversarial perturbations and novel attack variants during training, hardening it against the manipulation techniques that real adversaries deploy. This matters because machine learning based detectors are famously brittle: small, carefully crafted changes to input data can flip a malicious event into the benign category. By exposing the model to such manipulations before deployment, the framework aims to close that gap proactively rather than discovering it during a live incident.

The empirical results are the headline numbers. Tested on three widely used benchmark datasets, UNSW NB15, CIC IDS2018, and VeReMi, the latter being a standard reference dataset for vehicular misbehavior, the framework achieved detection accuracy above 96 percent. Against novel attack variants, it demonstrated more than 30 percent improved robustness, a measure of how well the detector holds up when confronted with threats it has not seen during training. Perhaps most important for real-world scalability, the communication overhead per federated learning round stayed below 4 megabytes, a crucial figure because bandwidth in congested vehicular networks is scarce and every megabyte exchanged between vehicles and aggregators competes with safety-critical traffic information.

The researchers have also made reproducibility a priority in a field where it is often lacking. The complete implementation and network hierarchical configuration code is publicly accessible through a Google Colab notebook, allowing other researchers and practitioners to verify the results and build on the work. The authors declare no competing interests and no external funding for the research, and the study appears in Cluster Computing, Volume 29, as article number 797, published on 27 September 2026.

The significance of this work extends beyond one detection algorithm. It sketches a template for how security in large-scale cyber-physical systems might be governed in the future: intelligence distributed to the edge, trust computed and enforced through tamper-evident ledgers, evidence preserved in a way that survives disputes, and governance rules that adapt autonomously as threats evolve. For the Internet of Vehicles specifically, where a successful attack can translate directly into physical danger on the road, the combination of privacy-preserving learning, trust-weighted aggregation, and fast forensic retrieval addresses the full lifecycle of a security incident, from detection through investigation. Challenges certainly remain, including the overhead of blockchain operations at city scale, the difficulty of bootstrapping trust among strangers on the road, and the relentless creativity of attackers. But IoV BCFL+ demonstrates that these pieces can be assembled into a coherent, tested architecture, and it offers next-generation intelligent transportation systems a credible path toward security that scales with the fleet and evolves with the threat landscape.

Subject of Research: Blockchain-enabled federated learning for intrusion detection in Internet of Vehicles networks

Article Title: Blockchain-enabled federated learning with spatio-temporal trust and self-evolving governance for IoV intrusion detection

Article References: Durga Charan, K., & Vishnukumar, R. (2026). Blockchain-enabled federated learning with spatio-temporal trust and self-evolving governance for IoV intrusion detection. Cluster Computing, 29(14), Article 797. https://doi.org/10.1007/s10586-026-06621-9

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06621-9

Keywords: Internet of Vehicles, federated learning, blockchain, intrusion detection, cybersecurity, spatio-temporal intelligence, trust management, connected vehicles, forensics, adversarial robustness, smart contracts, privacy preservation

The technique, called qBiCo, is described in the open-access journal Epigenetics Communications. It is a five-plex, TaqMan probe-based quantitative PCR assay that amplifies both single-copy genes and repetitive elements in bisulfite-converted DNA, the modified molecule that nearly every methylation experiment actually measures. From a single reaction, qBiCo estimates four critical parameters: the concentration of converted DNA, its degree of fragmentation, the global conversion efficiency, and the presence of inhibitors that could derail PCR amplification downstream.

The need for such a tool stems from an awkward chemical compromise. Bisulfite conversion works by treating DNA with sodium bisulfite at low pH and elevated temperature, converting unmethylated cytosines into uracils while leaving methylated cytosines untouched. Subsequent PCR replaces the uracils with thymines, so methylation patterns appear as C-to-T sequence variants readable by microarrays, pyrosequencing or massively parallel sequencing. But the same aggressive conditions that perform the conversion also attack the DNA itself. Sodium bisulfite causes depyrimidination and generates abasic sites prone to strand breaks, meaning the treated molecule is fragmented, mostly single-stranded and contaminated with carryover chemicals. Choose gentler conditions and the conversion becomes incomplete, leading to overestimated methylation and misinterpreted data. Choose harsher conditions and the DNA shatters beyond use.

Despite these well-known hazards, most epigenetics researchers have relied on manufacturer promises of greater than 99 percent conversion efficiency, at least 80 percent recovery and eluted fragments up to 2,000 base pairs long. Existing assessment approaches have been piecemeal: Nanodrop spectrophotometry, Qubit fluorometry and Bioanalyzer fragment analysis were never designed for the peculiar, hybrid single- and double-stranded nature of bisulfite-converted DNA. Earlier targeted assays, such as one developed by Ehrich and colleagues, measured fragmentation at increasing incubation temperatures but said nothing about conversion efficiency, while single-locus approaches risked severe bias. None offered a global picture in one test.

The Rotterdam team, led by Athina Vidaki together with Faidra Karkala and colleagues, designed qBiCo around two carefully chosen target classes. A short fragment of the single-copy hTERT gene reports converted DNA concentration, while a longer fragment of the same gene provides a fragmentation index. Two assays target the genomic and converted versions of LINE1, a repetitive element that constitutes roughly 17 percent of the human genome, allowing conversion efficiency to be measured across hundreds of genomic copies rather than a single locus. Because each LINE1 probe interrogates five cytosines across approximately 180 to 200 genomic regions, the efficiency measure is far more representative than comparable systems, such as BisQuE, which relies on a single cytosine in one gene intron. A fifth assay, a spiked-in artificial fragment, acts as an internal positive control flagging PCR inhibition.

Because no reliable standard exists for quantifying converted DNA, the team built synthetic DNA fragments, or gBlocks, mimicking the exact sequences their assays produce, mixed in ratios that resemble natural human converted DNA. Validation showed PCR efficiencies between 90 and 99 percent, linear detection down to picogram quantities, and striking robustness: conversion efficiency readings held steady even in the presence of extremely high levels of the PCR inhibitor hematin. Only artificial DNA degradation, induced by even one minute of UV exposure, meaningfully disturbed the readings.

The real drama came when the researchers applied qBiCo to ten commercial bisulfite conversion kits across DNA inputs ranging from 200 nanograms down to 1 nanogram. Recovery of converted DNA ranged from a sobering 8.5 to 100 percent, and conversion efficiencies from 78 to 99.9 percent, a spread that flatly contradicts the universal promises on the packaging. One kit failed systematically, producing conversion rates as low as 2 percent. Others lost more than 70 percent of the input DNA, while a handful, notably kits from Diagenode, Sigma Aldrich and Qiagen, maintained conversion efficiency above 95 percent even at the lowest inputs. Fragmentation proved pervasive: even with the best-performing kit, the intact portion of DNA fragments at least 235 base pairs long was no more than 50 to 60 percent of the sample, and longer fragments became undetectable at 10-nanogram inputs.

These results echo and extend earlier warnings. A 2018 study by Kint and colleagues had already reported kit recoveries ranging from 26.6 to 88.3 percent using a cumbersome multi-method approach that consumed precious sample. Even the inventor of bisulfite conversion, Hikoya Hayatsu, cautioned in 2008 that available methylation data needed careful re-examination and that a scientifically sound, assured methodology should be established as soon as possible. The qBiCo team argues that the field has, in effect, been running on assumption, and that no bisulfite-converted-DNA-specific method existed until now to hold the process accountable.

Determined to turn the assay into a practical tool, the researchers built an improved prototype, qBiCo-v2. They replaced the weakest assay, a long hTERT fragment, with a 222-base-pair target from the TPT1 gene, halved the reaction volume to 10 microliters, refined the synthetic standard using data from sixteen different conversion kits, and developed a semi-automated spreadsheet pipeline that calculates all four indices directly from raw qPCR output. Crucially, they transferred the method to six qPCR platforms from three major manufacturers, BioRad, Thermo Fisher Scientific and Qiagen, and validated it on each, finding comparable quantification cycles across instruments and establishing a detection limit of 150 picograms of input DNA.

The implications reach well beyond the bench. DNA methylation biomarkers are moving toward clinical implementation in cancer detection, ageing research and forensic science, settings where standardization is paramount and where scarce or degraded samples, such as cell-free tumor DNA or crime-scene traces, make every molecule count. The authors call on epigenetics researchers to shift from assuming their conversion kits work to measuring them empirically, integrating qBiCo as a routine quality-control step regardless of the downstream analysis. If they succeed, a reaction that has quietly shaped two decades of epigenetic data may finally get the scrutiny it has always needed, and the methylation maps of the future could rest on far firmer ground.

Subject of Research: Quality control of bisulfite-converted DNA methylation analysis using quantitative PCR

Article Title: qBiCo: a method to assess global DNA conversion performance in epigenetics via single-copy genes and repetitive elements

Article References: Karkala, F., Simons, R. B., Claessens, F., Kalamara, V., Kayser, M., & Vidaki, A. (2025). qBiCo: a method to assess global DNA conversion performance in epigenetics via single-copy genes and repetitive elements. Epigenetics Communications, 5(1), Article 2. https://doi.org/10.1186/s43682-025-00033-3

Image Credits: AI Generated

DOI: 10.1186/s43682-025-00033-3

Keywords: DNA methylation, bisulfite conversion, epigenetics, qPCR, quality control, LINE1, hTERT, DNA fragmentation, biomarkers, forensics, kit validation, standardization