Formal-methods researcher bridging information integrity and AI security, from fact-checking to AI-SOC defense
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
4
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: publication-volume data is insufficient in this snapshot. Output would measure total and per-year work counts, venue spread, and first/corresponding-author share across the full record, beyond the two papers reviewed here.
Impact—
Not yet scored: citation data is insufficient here. Impact would measure citations, uptake, and influence of the works; the sparse on-file indicators (h-index 4, i10-index 2) are reported verbatim but not scored.
Focus0/100
Scores 0/100, reflecting a deliberately split portfolio: the field distribution divides evenly (50% AI/LLM security in security operations, 50% computational fact-checking/formal methods in information integrity), and topic mass spreads across five clusters led by Formal Methods in Verification (17), plus logic and type systems (6), modeling and simulation (6), testing and debugging (4), and adversarial robustness (3). Breadth, not single-track concentration, characterizes this record.
Collaboration51/100
Scores 51/100, a mid-range collaboration profile. The record lists 12 distinct coauthors, and recurring partners include Panagiotis Katsaros, Grigorios Tsoumakas, Andreas Veglis, Michael Sirivianos, and Charalampos Bratsas. Both 2026 catalog papers are team efforts, but with different roles: first author on the fact-checking SoK and a middle position on the AI-SOC framework, neither as corresponding author — suggesting contribution through co-authored teams rather than solo-led projects.
Activity47/100
Scores 47/100, consistent with a modest but continuing output rhythm. Counts by year show 2 works in 2017, 4 in 2018, a peak of 5 in 2020, 2 in each of 2021 and 2022, then 1 in 2023 and 1 in 2024 before rebounding to 3 in 2026; 4 works fall within the most recent three-year window. Output persists across nearly a decade without sustained high volume.
Reproducibility20/100
Scores 20/100 (reproMean 20, based on 2 reviewed papers), the weakest measured axis. Both Evolve-reviewed papers carry low repro-readiness: the fact-checking SoK is a survey whose negatives the review notes are corpus-relative, and the AI-SOC framework's evidence rests on 20 self-authored synthetic attacks. No artifact, dataset, or benchmark release is documented in the reviewed material, so reproduction currently depends on external reimplementation.
Research summary
Nikolaos Kekatos (Larnaca College, Cyprus; ORCID 0009-0000-2358-4270) works at the intersection of formal methods and applied security. His OpenAlex record (identity: openalex) is led by Formal Methods in Verification with 17 works, followed by logic, programming, and type systems (6), modeling and simulation systems (6), software testing and debugging techniques (4), and adversarial robustness in machine learning (3). Publication activity spans 2017–2026: 2 works in 2017, 4 in 2018, a peak of 5 in 2020, 2 in each of 2021 and 2022, 1 in each of 2023 and 2024, and 3 in 2026; 4 works fall in the most recent three years, with h-index 4 and i10-index 2. Two 2026 arXiv papers anchor the qualitative picture: a first-authored SoK organizing 121 fact-checking works into a five-level formal-methods stack, and a co-authored neurosymbolic framework pairing Wazuh with NeMo Guardrails to defend AI-SOC pipelines against prompt injection. Radar scores are activity 47/100, collaboration 51/100, reproducibility 20/100, and focus 0/100, with output and impact unscored for insufficient data.
Collaboration pattern
Nikolaos Kekatos's OpenAlex record lists 12 distinct coauthors, with recurring partners including Panagiotis Katsaros, Grigorios Tsoumakas, Andreas Veglis, Michael Sirianos, and Charalampos Bratsas. The collaboration score is 51/100 — mid-range. In the two Evolve-reviewed 2026 papers the roles differ: first author, not corresponding, on the fact-checking SoK, and a middle author position on the AI-SOC framework. The pattern suggests team-based co-authorship across security and information-integrity projects rather than solo or corresponding-author-led work.
Research keywords
Highlights
First-authored SoK orders 121 fact-checking works into a five-level formal-methods stack
Neurosymbolic two-layer defense for the AI security operations center
Timeline
- 2017Earliest recorded works appear: 2 works in the OpenAlex counts-by-year record.
- 2020Peak annual output in the record: 5 works recorded.
- 2022Mid-decade rhythm holds at 2 works, following 2 in 2021.
- 2024Quietest stretch of the record: 1 work in each of 2023 and 2024.
- 20263 works recorded, including both Evolve-reviewed arXiv papers: the first-authored fact-checking SoK and the AI-SOC neurosymbolic framework.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric indicators (h-index 4, i10-index 2, per-year counts, coauthor counts) come from an OpenAlex identity record and may be incomplete or affected by name disambiguation.
- Output and impact dimensions are unscored in this snapshot because the underlying data is insufficient; no citation totals were available.
- Qualitative assessment rests on only two Evolve-reviewed papers, both 2026 arXiv preprints; other works in the record were not reviewed.
- The reproducibility score (reproMean 20) is computed from these 2 reviewed papers only and may change as more works are reviewed.