Early-career ML researcher bridging adversarially robust DDoS detection and web browsing behavior mining
3
papers here
3
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
9
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
No publication-count or output data is available in this snapshot, so the output axis is unscored. It would measure the volume and cadence of scholarly output — total papers, venues, and preprints over time — once such records are indexed.
Impact—
Impact is unscored because no citation counts, h-index, or influence metrics exist in this snapshot. This axis would measure how widely the work is cited and taken up by other researchers, and can be computed once citation records are linked.
Focus0/100
The focus score is 0, reflecting an even split of the cataloged portfolio: fieldDist assigns 0.5 to network security (adversarial machine learning) and 0.5 to web mining, user modeling, and privacy (machine learning). With only two 2026 papers, neither field yet dominates; this axis measures the concentration of output across fields and will stabilize as more publications accumulate.
Collaboration46/100
Collaboration scores 39, based on 6 distinct coauthors in the snapshot. Recurring collaborators include Rida Khatoun (appearing twice in the frequent-coauthor records), Omran Berjawi, Makram Chehayeb, Amina Rizk, and Ralph Elsaghbini. Both catalog papers are middle-authored and non-corresponding, consistent with a contributing member of compact teams; the moderate score reflects a small but stable network so far.
Activity61/100
Activity is unscored: the snapshot lacks per-year publication volume and recency signals beyond the two 2026 preprints. This axis would measure publishing tempo and scholarly engagement across consecutive years, which requires a longer indexed history to evaluate.
Reproducibility43/100
Reproducibility averages 38 across the 2 papers assessed. The GAN-based DDoS detection paper is rated low for reproducibility readiness, with the review citing ambiguous evaluation details; the behavioral fingerprinting paper reaches medium and is described as a transparent study, though its LLM comparisons lack statistical tests. This axis measures how readily others can rerun and verify reported results.
Research summary
Walid Fahs is an early-stage machine learning researcher whose cataloged work to date spans two adjacent areas: adversarially robust network security and the mining of web browsing behavior. Both papers in the Evolve catalog are 2026 arXiv preprints on which Fahs is a middle-listed, non-corresponding author, indicating participation in small collaborative teams rather than solo or senior-led efforts. The first applies WGAN-GP-based data augmentation and adversarial training to DDoS detection on the CICDDoS2019 dataset; Evolve's review found that the augmentation lifts detector robustness in synthetic evasion tests, while cautioning that naive threat modeling and ambiguous evaluation details weaken real-world claims. The second quantifies behavioral fingerprinting in web usage: about 90% of users are identifiable from short sessions and next visited domains are predicted with roughly 80% accuracy using GraphSAGE; the study was judged transparent, though sub-point LLM gains lacked statistical testing. The bibliometric snapshot records 6 distinct coauthors, an even 50/50 split across the two fields (focus score 0), a collaboration score of 39, and a reproducibility score of 38 averaged over two assessed papers. Output, impact, and activity metrics are not yet available, so this should be read as an early-stage profile.
Collaboration pattern
The snapshot records 6 distinct coauthors and a collaboration score of 39. Frequent collaborators include Rida Khatoun — listed twice in the coauthor records — alongside Omran Berjawi, Makram Chehayeb, Amina Rizk, and Ralph Elsaghbini. On both cataloged papers Fahs is a middle-listed, non-corresponding author, suggesting a reliable contributor within a small, stable group working across network security and web-behavior mining.
Research keywords
Highlights
GAN-based augmentation hardens DDoS detectors — with caveats
~90% of users identifiable from short browsing sessions
Timeline
- 2026Co-authored (middle position) 'A GAN-Based Framework for Robust DDoS Attack Detection' appears on arXiv, applying WGAN-GP data augmentation and adversarial training to DDoS detection.
- 2026Co-authored (middle position) 'Behavioral Fingerprinting and Navigation Prediction in Web Browsing' appears on arXiv, reporting about 90% user identification and roughly 80% next-domain prediction accuracy.
- 2026Both papers enter the Evolve catalog with review verdicts and reproducibility-readiness ratings (low and medium, respectively).
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.
- Institution and country are not recorded; this profile is name-resolved from public bibliographic data and ORCID 0000-0002-6077-6519.
- Only two papers, both 2026 arXiv preprints, are in the Evolve catalog; the full publication record may be larger.
- Output, impact, and activity dimensions are unscored because the underlying bibliometric data is not available in this snapshot.
- Collaboration, focus, and reproducibility scores come from the provided bibliometric snapshot; paper-level assessments come from Evolve's own reviews.