About

Lou Chitkushev is a Professor of Computer Science at Boston University Metropolitan College. He holds the position of Senior Associate Dean, Academic Affairs, and serves as the Director of Health Informatics and Health Sciences. Additionally, he is the Head of the Digital Forensics Research Laboratory. His roles indicate a focus on health informatics, digital forensics, and related areas within computer science. The page highlights his leadership positions and contributions to academic affairs and research in these fields, emphasizing his involvement in health sciences and digital forensics research.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Medicine
• Internal medicine
• Natural Language Processing
• Genetics
• Computational biology
• Biology
• Pathology
• Medical physics
• Immunology
• Evolutionary biology
• Finance
• Virology
• Radiology
• Economics

Selected publications

• Forensic Output Scale (FOS): Dataset of 79 Deepfake Detection Methods Classified by Forensic Output Type

  Zenodo (CERN European Organization for Nuclear Research) · 2026-05-14

  datasetOpen accessSenior author

  This dataset accompanies the paper "Detecting Deepfakes for the Courtroom: A Multi-Modal Forensic Output Framework" (EAI CSECS 2026). It catalogs 79 deepfake detection methods across image, video, audio-visual, and audio modalities, classified by the Forensic Output Scale (FOS), a five-level taxonomy of detector output types: L0 Detection (score/probability), L1 Localization (where), L2 Attribution (what generator/method), L3 Narration (natural-language explanation), and L4 Verification (a specific, juror-checkable factual claim). The dataset reveals that 57% of surveyed methods (45/79) ship only L0 outputs, while no method currently produces L4 verification output. Seven methods compute L4-capable internal signals (mouth temporal anomalies, action unit relationships, blood-flow rPPG, lip-audio alignment, pupil geometry, etc.) but collapse them to scalar scores at inference — a gap we term the "L4 readiness gap." Contents (10 sheets): README — taxonomy definitions and dataset documentation Methods — master catalog of all 79 methods with year, venue, modality, FOS level, output type, internal signal (if L4-capable), notes, and Chicago author-date reference L0 Detection / L1 Localization / L2 Attribution / L3 Narration / L4 Verification — methods split by FOS level L4-Capable (ships L0) — the seven detectors with internal verifiable signals plus the L4 claim each would produce if surfaced and how a juror could verify it Datasets — 21 evaluation datasets supporting explainable deepfake detection Summary — distribution statistics across FOS levels and modalities Intended use: Forensic practitioners selecting court-admissible detectors, researchers identifying gaps in explainability, and policy/legal scholars assessing detector suitability under Daubert and analogous evidence standards.

  PublisherDOI

• Global Insights and Collaborative Frameworks: Advancing International Security Through the Boston University-Korean National Police University Summer Study Abroad Program

  2026-03-31

  book-chapterSenior author

  The Intelligence and National Security Focused Summer Study Abroad Program is a collaboration between Boston University Metropolitan College (BU MET) and the Korean National Police (KNP). Held in July 2024 in Boston, this two-week program aimed to enhance expertise in global law enforcement and intelligence operations among six KNP professionals. Participants engaged in a curriculum designed to deepen their understanding of both theoretical and practical aspects, focusing on threat assessments, intelligence tactics, cyber intelligence, and cryptocurrency investigations. The program’s objectives were to provide practical insights into complex security operations, bridge theoretical constructs with real-world applications, and promote international cooperation to address global security challenges. This paper examines the program’s structured approach, the challenges encountered—such as aligning objectives, handling sensitive information, logistical barriers, cultural differences, and time constraints—and explores future directions to enhance the program’s impact and sustainability. Through this initiative, BU MET and KNP underscore their commitment to advancing global security expertise and strengthening international relationships through academic and professional collaborations.

  PublisherDOI

• Forensic Output Scale (FOS): Dataset of 79 Deepfake Detection Methods Classified by Forensic Output Type

  Zenodo (CERN European Organization for Nuclear Research) · 2026-05-15

  datasetOpen accessSenior author

  This dataset accompanies the paper "Detecting Deepfakes for the Courtroom: A Multi-Modal Forensic Output Framework" (EAI CSECS 2026). It catalogs 79 deepfake detection methods across image, video, audio-visual, and audio modalities, classified by the Forensic Output Scale (FOS), a five-level taxonomy of detector output types: L0 Detection (score/probability), L1 Localization (where), L2 Attribution (what generator/method), L3 Narration (natural-language explanation), and L4 Verification (a specific, juror-checkable factual claim). The dataset reveals that 57% of surveyed methods (45/79) ship only L0 outputs, while no method currently produces L4 verification output. Seven methods compute L4-capable internal signals (mouth temporal anomalies, action unit relationships, blood-flow rPPG, lip-audio alignment, pupil geometry, etc.) but collapse them to scalar scores at inference — a gap we term the "L4 readiness gap." Contents (10 sheets): README — taxonomy definitions and dataset documentation Methods — master catalog of all 79 methods with year, venue, modality, FOS level, output type, internal signal (if L4-capable), notes, and Chicago author-date reference L0 Detection / L1 Localization / L2 Attribution / L3 Narration / L4 Verification — methods split by FOS level L4-Capable (ships L0) — the seven detectors with internal verifiable signals plus the L4 claim each would produce if surfaced and how a juror could verify it Datasets — 21 evaluation datasets supporting explainable deepfake detection Summary — distribution statistics across FOS levels and modalities Intended use: Forensic practitioners selecting court-admissible detectors, researchers identifying gaps in explainability, and policy/legal scholars assessing detector suitability under Daubert and analogous evidence standards.

  PublisherDOI

• Forensic Output Scale (FOS): Dataset of 79 Deepfake Detection Methods Classified by Forensic Output Type

  Zenodo (CERN European Organization for Nuclear Research) · 2026-05-14

  datasetOpen accessSenior author

  This dataset accompanies the paper "Detecting Deepfakes for the Courtroom: A Multi-Modal Forensic Output Framework" (EAI CSECS 2026). It catalogs 79 deepfake detection methods across image, video, audio-visual, and audio modalities, classified by the Forensic Output Scale (FOS), a five-level taxonomy of detector output types: L0 Detection (score/probability), L1 Localization (where), L2 Attribution (what generator/method), L3 Narration (natural-language explanation), and L4 Verification (a specific, juror-checkable factual claim). The dataset reveals that 57% of surveyed methods (45/79) ship only L0 outputs, while no method currently produces L4 verification output. Seven methods compute L4-capable internal signals (mouth temporal anomalies, action unit relationships, blood-flow rPPG, lip-audio alignment, pupil geometry, etc.) but collapse them to scalar scores at inference — a gap we term the "L4 readiness gap." Contents (10 sheets): README — taxonomy definitions and dataset documentation Methods — master catalog of all 79 methods with year, venue, modality, FOS level, output type, internal signal (if L4-capable), notes, and Chicago author-date reference L0 Detection / L1 Localization / L2 Attribution / L3 Narration / L4 Verification — methods split by FOS level L4-Capable (ships L0) — the seven detectors with internal verifiable signals plus the L4 claim each would produce if surfaced and how a juror could verify it Datasets — 21 evaluation datasets supporting explainable deepfake detection Summary — distribution statistics across FOS levels and modalities Intended use: Forensic practitioners selecting court-admissible detectors, researchers identifying gaps in explainability, and policy/legal scholars assessing detector suitability under Daubert and analogous evidence standards.

  PublisherDOI

• SeFS: A Secure and Efficient File Sharing Framework based on the Trusted Execution Environment

  ICST Transactions on Security and Safety · 2025-07-18

  articleOpen accessSenior author

  As the cloud-based file sharing becomes increasingly popular, it is crucial to protect the outsourced data against unauthorized access. Existing cryptography-based approach suffers from expensive re-encryption upon permission revocation. Other solutions that utilize Trusted Execution Environment (TEE) to enforce access control either expose the plaintext keys to users or turn out incapable of handling concurrent requests. In this paper, we propose SeFS, a secure and practical file sharing framework that leverages cooperation of server-side and client-side enclaves to enforce access control, with the former responsible for registration, authentication and access control enforcement and the latter performing file decryption. Such design significantly reduces the computation workload of server-side enclave, thus capable of handling concurrent requests. Meanwhile, it also supports immediate permission revocation, since the file decryption keys inside the client-side enclaves are destroyed immediately after use. We implement a prototype of SeFS and the evaluation demonstrates it enforces access control securely with high throughput and low latency.

  PublisherOA PDFDOI

• Global Insights and Collaborative Frameworks: Advancing International Security Through the Boston University-Korean National Police University Summer Study Abroad Program

  Journal of Criminal Justice Education · 2025-07-03

  articleSenior author
  PublisherDOI

• Balancing Public Safety and Privacy: A Media Analysis of Robotic Technology in Law Enforcement

  Journal of Applied Security Research · 2025-07-11

  articleSenior author
  PublisherDOI

• PREDBL6: a system for predicting C57BL/6 mouse T-cell epitopes

  2024-12-03

  article

  The MHC class I antigen processing pathway plays a critical role in the adaptive immune system by presenting peptides for recognition by CD8+ T cells. While most prediction tools focus on MHC binding, accurately identifying immunogenic T-cell epitopes requires accounting for additional factors such as antigen processing and peptide-MHC binding thermostability. We developed a bioinformatics tool that integrates MHC binding predictions with thermostability assessment and antigen processing steps to enhance T cell epitope identification accuracy for C57BL/6 mice. Our machine learning models, trained on a comprehensive dataset of eluted H2-K<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">b</sup> and H2-D<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">b</sup> ligands and thermostability data across a range of physiologically relevant temperatures (37°C, 50°C, 70°C), were rigorously validated. These models showed improved overall accuracy on an external validation dataset compared to the widely used NetMHCPan-4.1. We consolidated the models into a user-friendly web-based application named PREDBL6 to facilitate accurate predictions of immunogenic peptides that stably bind H2b molecules and stimulate immune responses in C57BL/6 mice. PREDBL6 is accessible at http://met-hilab.org:3001/.

  PublisherDOI

• Understanding Worldwide Natural Gas Trade Flow for 2017 to 2022: A Network-Based Approach

  Communications in computer and information science · 2024-01-01 · 2 citations

  book-chapter
  PublisherDOI

• XKidneyOnco: An Explainable Framework to Classify Renal Oncocytoma and Chromophobe Renal Cell Carcinoma with a Small Sample Size

  bioRxiv (Cold Spring Harbor Laboratory) · 2024-01-25 · 2 citations

  preprintOpen access

  Abstract Renal oncocytoma and chromophobe renal cell carcinoma are two kidney cancer types that present a diagnostic challenge to pathologists and other clinicians due to their microscopic similarities. While RO is a benign renal neoplasm, ChRCC is considered malignant. Therefore, the differentiation between the two is crucial. In this study, we introduce an explainable framework to accurately differentiate ChRCC from RO, histologically. Our approach examined H&amp;E-stained images of 656 ChRCC and 720 RO, and achieved a diagnostic accuracy of 88.2%, the sensitivity of 87%, and 100% specificity for explainable AI, which either outperforms or operate on par with convolutional neural network (CNN) models. Besides, we enrolled 44 pathology experts (including pathologists and pathology trainees) to differentiate the two tumors. The average accuracy of pathologists was 73%, which is 15.2% lower than our framework. These results indicate that the combination of human expert along with explainable AI achieve higher accuracy in differentiating the two tumors, while it reduces the workload of experts and offers the desired explainability for the medical experts.

  PublisherOA PDFDOI

Frequent coauthors

• Derin B. Keskin

  Boston University

  54 shared

• Guanglan Zhang

  Boston University

  45 shared

• Vladimir Brusić

  University of Nottingham Ningbo China

  37 shared

• Irena Vodenska

  Saints Cyril and Methodius University of Skopje

  30 shared

• Guang Lan Zhang

  29 shared

• John Day

  Kaiser Permanente

  22 shared

• Eduard Grasa

  i2CAT

  16 shared

• Reza Rawassizadeh

  Institute for Health Metrics and Evaluation

  13 shared

Education

• Ph.D.

  Boston University

• M.S.

  Medical College of Virginia

• M.S.

  University of Belgrade

• B.S.

  University of Belgrade

Awards & honors

• Best Presentation Award (2014)