I am an AI Researcher at MIT Lincoln Lab. I earned my Ph.D. in Information Sciences and Technology at The Pennsylvania State University under the guidance of Dr. Dongwon Lee at the PIKE Lab in August 2023. While at Penn State, I was a Button-Waller Fellow, an NSF Scholarship for Service Scholar, and an Alfred P. Sloan Scholar. I earned a B.S. in Mathematics, with a minor in Statistics at University of Maryland Baltimore County (UMBC) in May 2018. While at UMBC, I was a McNair scholar and a member of Pi Mu Epsilon (the Mathematical Honorary Society). My research interests are: Artificial Intelligence, Machine Learning, and Data mining in the application domain of Cybersecurity. Specifically, I am interested in:

  • NLP (Natural Language Processing)
  • NLG (Natural Language Generation), such as Large Language Models (LLMs)
  • Adversarial Robustness & Adversarial Machine Learning
  • TDA (Topological Data Analysis)


News

Toggle Old News
  • Apr 2025 - Invited to serve as Senior Area Chair (SAC) for EMNLP 2025
  • Mar 2025 - A new preprint, about investigating the prevalence of machine-generated texts in disinformation datasets - Beyond speculation: Measuring the growing presence of LLM-generated texts in multilingual disinformation
  • Mar 2025 - 1 paper on Obfuscation and Impersonation attacks accepted to NLP4DH
  • Mar 2025 - Served on a panel for UMBC McNair's Let's Talk Grad School (LTGS) #3: Careers After Graduate School
  • Feb 2025 - Invited to serve as Area Chair for ACL RR (ACL 2025)
  • Feb 2025 - Invited to Panels & Workshops reviewer for the 2025 Tapia conference
  • Jan 2025 - Invited to serve as a PC member at ECAI 2025 conference
  • Jan 2025 - 2 papers accepted to NAACL 2025 - PlagBench and Beemo
  • Nov 2024 - A new preprint on a comprehensive survey of Topological Data Analysis applications in NLP, titled Unveiling Topological Structures in Text: A Comprehensive Survey of Topological Data Analysis Applications in NLP is available
  • Nov 2024 - A new preprint, titled Beemo: Benchmark of Expert-edited Machine-generated Outputs is available
  • Oct 2024 - Invited to review for Nature Human Behaviour and to serve as PC member for NAACL-HLT/ACL/EMNLP Tutorials 2025
  • Sep 2024 - Selected to participate in the 2025 EWM-EMS Summer School: Stability in Topological Data Analysis at Institut Mittag-Leffler
  • Sep 2024 - 1 paper on Evaluating the Adversarial robustness of multi-lingual deepfake text detector - Authorship Obfuscation in Multilingual Machine-Generated Text Detection has been accepted to EMNLP-Findings 2024
  • Jul 2024 - Invited to serve as a PC member at Workshop on Detecting AI Generated Content (DAIGenC) @ COLING 2025 conference
  • Jul 2024 - Invited to serve on a virtual panel of professionals to speak to USM LSAMP Summer Research Fellows about career pathways.
  • Jul 2024 - Selected to participate in the 2024 Dagstuhl Seminar - "Fair Division: Algorithms, Solution Concepts, and Applications"
  • Jul 2024 - 1 paper on Deepfake Text Detection with Topological Data Analysis accepted to ECAI 2024, titled TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles
  • Jun 2024 - A new preprint titled, PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
  • May 2024 - Invited to be a Reviewer for Widening Natural Language Processing (WiNLP) 2024
  • May 2024 - 1 paper on the philosophical paradox of authorship before and after authorship masking - A Ship of Theseus has been accepted to ACL'24
  • May 2024 - Invited to give a talk at the Geo Regional African Group at Cohere for AI
  • Apr 2024 - Selected to participate in the 11th Heidelberg Laureate Forum (HLF) 2024
  • Mar 2024 - 1 paper on using statistical psycholinguistic features to detect Deepfake Texts - GPT-who has been accepted to NAACL-Findings'24
  • Mar 2024 - Invited to be a PC member at ECAI 2024 conference
  • Jan 2024 - Upcoming Invited Talk at St. George's University, Grenada on Feb 15th
  • Jan 2024 - A new preprint titled, Authorship Obfuscation in Multilingual Machine-Generated Text Detection is available
  • Dec 2023 - Attended EMNLP 2023 in person for 3 accepted papers - MULTITuDE, F3, and HANSEN
  • Nov 2023 - A new preprint titled, A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts is available
  • Oct 2023 - Tutorial: Catch Me If You GPT: Tutorial on Deepfake Texts accepted at NAACL 2024
  • Oct 2023 - A new preprint titled, GPT-who: An Information Density-based Machine-Generated Text Detector is available
  • Sep 2023 - A new preprint titled, TopRoBERTa: Topology-Aware Authorship Attribution of Deepfake Texts is available



    • Press Mentions: