News & Updates

Selected milestones (papers, submissions, grants, talks). For the most complete record, see the CV and Google Scholar.

2026

  • 2026 Mar 2026: Three undergraduate coauthored papers were accepted for presentation and publication in the online MICS 2026 proceedings: Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers; Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2; and Empirical Evaluation of Data Poisoning Attacks and Practical Defenses in Supervised Learning.
  • 2026 Mar 2026: Submitted the corresponding full-paper versions for the three accepted MICS 2026 papers to the conference proceedings system.
  • 2026 Jan 2026: Submitted work on a controlled evaluation of prompted LLM inference vs. fine-tuned encoders (under review).
  • 2026 2026: Green NLP for Online Abuse Detection and Caption-then-Classify for Multimodal Harmful Meme Detection are under revision for resubmission.
  • 2026 Spring 2026: Launched the Trustworthy Language Intelligence Lab (TLI Lab) as the research home for security-aware NLP, benchmarking, and efficiency-focused evaluation.

2025

  • 2025 COMPSAC 2025: Published comparative analysis of transformer vs. traditional ML models for cyberbullying detection (DOI).
  • 2025 Dec 2025: Submitted curated UHS Twitter/X dataset and documentation for incident-response utility (under review).
  • 2025 Oct 2025: Presented “CyberTweetGrader&Labeler: Social Media Analytics for Cyberattack Intelligence” at the ND EPSCoR Annual State Conference.
  • 2025 2025–2026: Faculty Small Grant funded to expand and validate CTGL.

2024

  • 2024 MICS 2024: Student-mentored publications on FIFA World Cup sentiment/theme analysis and AI vs. human text detection.
  • 2024 Apr 2024: Co-coordinated the Minot State AI & Data Summit (student posters + mentoring).

Earlier

  • 2023 ICAIIC 2023: Published “Twitter User Sentiments Analysis: Health System Cyberattacks Case Study.”

© Muhammad Abusaqer