About

Lixia Zhang is a Distinguished Professor in the Department of Computer Science and Electrical and Computer Engineering at UCLA Samueli School of Engineering. She holds the Jonathan B. Postel Chair in Computer Systems Engineering. Her research interests include cybersecurity and the future internet, internet architecture and protocol designs, security in large scale and open systems, and Named Data Networking. Dr. Zhang earned her PhD from MIT in 1989. She has received numerous awards and recognitions, including the Omidyar Network Award in 2023, membership in the Internet Hall of Fame in 2021, a Lifetime Achievement Award for work on Communication Networks, and fellowships from ACM and IEEE. Her contributions significantly impact the development of secure and scalable internet systems.

Research topics

• Computer Security
• Computer Science
• Business
• Internet privacy
• Computer network
• Operating system
• World Wide Web
• Telecommunications

Selected publications

• Intelligent Pathological Diagnosis of Gestational Trophoblastic Diseases via Visual-Language Deep Learning Model

  ArXiv.org · 2026-03-03

  articleOpen access

  The pathological diagnosis of gestational trophoblastic disease(GTD) takes a long time, relies heavily on the experience of pathologists, and the consistency of initial diagnosis is low, which seriously threatens maternal health and reproductive outcomes. We developed an expert model for GTD pathological diagnosis, named GTDoctor. GTDoctor can perform pixel-based lesion segmentation on pathological slides, and output diagnostic conclusions and personalized pathological analysis results. We developed a software system, GTDiagnosis, based on this technology and conducted clinical trials. The retrospective results demonstrated that GTDiagnosis achieved a mean precision of over 0.91 for lesion detection in pathological slides (n=679 slides). In prospective studies, pathologists using GTDiagnosis attained a Positive Predictive Value of 95.59% (n=68 patients). The tool reduced average diagnostic time from 56 to 16 seconds per case (n=285 patients). GTDoctor and GTDiagnosis offer a novel solution for GTD pathological diagnosis, enhancing diagnostic performance and efficiency while maintaining clinical interpretability.

  PublisherOA PDF

• Intelligent Pathological Diagnosis of Gestational Trophoblastic Diseases via Visual-Language Deep Learning Model

  arXiv (Cornell University) · 2026-03-03

  preprintOpen access

  The pathological diagnosis of gestational trophoblastic disease(GTD) takes a long time, relies heavily on the experience of pathologists, and the consistency of initial diagnosis is low, which seriously threatens maternal health and reproductive outcomes. We developed an expert model for GTD pathological diagnosis, named GTDoctor. GTDoctor can perform pixel-based lesion segmentation on pathological slides, and output diagnostic conclusions and personalized pathological analysis results. We developed a software system, GTDiagnosis, based on this technology and conducted clinical trials. The retrospective results demonstrated that GTDiagnosis achieved a mean precision of over 0.91 for lesion detection in pathological slides (n=679 slides). In prospective studies, pathologists using GTDiagnosis attained a Positive Predictive Value of 95.59% (n=68 patients). The tool reduced average diagnostic time from 56 to 16 seconds per case (n=285 patients). GTDoctor and GTDiagnosis offer a novel solution for GTD pathological diagnosis, enhancing diagnostic performance and efficiency while maintaining clinical interpretability.

  PublisherDOI

• A Novel Multicriteria Decision‐Making Approach Incorporating Pythagorean Hesitant Fuzzy Sets for Endangered Species Habitat Selection

  Advances in Fuzzy Systems · 2026-01-01

  articleOpen access1st author

  Pythagorean hesitant fuzzy sets (PHFSs) effectively represent uncertain information in decision‐making by accommodating situations where the sum of membership and nonmembership degrees exceeds 1, provided their squared sum remains at most 1. This study proposes a novel distance measure for PHFSs and rigorously demonstrates its rationality and validity. By integrating this distance measure with conflict analysis, we define the conflict degree in Pythagorean hesitant fuzzy environments. Then a new multicriteria decision‐making (MCDM) method is developed to address problems with completely unknown criterion weights, avoiding artificial data manipulation based on decision‐makers’ risk preferences. The proposed distance measure serves as a key tool for quantifying dissimilarity between PHFSs while maintaining decision consistency and reliability. Finally, an illustrative example of habitat selection evaluation for endangered species, accompanied by comparative analysis, validates the effectiveness and feasibility of the proposed method.

  PublisherOA PDFDOI

• Diagnostic value of CEACAM6 and HE4 in pleural fluid for malignant pleural effusion

  Annals of Medicine · 2025-04-15 · 3 citations

  articleOpen access

  OBJECTIVE: This study aimed to assess the diagnostic performance of carcinoembryonic antigen-related adhesion molecule 6 (CEACAM6) and human epididymis protein 4 (HE4) in pleural fluid for the detection of malignant pleural effusion (MPE). MATERIALS AND METHODS: In this prospective study, pleural levels of CEACAM6 and HE4 were measured in two independent cohorts. The test cohort included 182 patients with exudative pleural effusions (123 malignant and 59 benign), and the validation cohort comprised 117 patients with exudative pleural effusions (65 malignant and 52 benign). Receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of CEACAM6 and HE4 for MPE. RESULTS: = .04). CONCLUSIONS: Pleural CEACAM6 and HE4 are promising biomarkers for distinguishing MPE from BPE. Their combination improves diagnostic accuracy, offering a valuable tool for MPE diagnosis, especially in challenging cases with cytology-negative pleural effusion.

  PublisherDOI

• A bias extraction and penalty method for robust visual question answering

  Applied Intelligence · 2025-11-01

  article1st authorCorresponding
  PublisherDOI

• Development of A Scoring System via An Interpretable End-to-end Neural Network for Prognostic Stratification of Patients with Advanced Melanoma

  Research Square · 2025-12-18

  preprintOpen access
  PublisherOA PDFDOI

• Enhanced Feature Extraction with Superlet Transformation for EEG Emotion Classification

  2024-08-23 · 3 citations

  article

  In the field of emotion recognition, electroencephalography(EEG) technology can accurately capture emotion, and has been widely used in psychology, public safety and other fields. In order to improve the accuracy and efficiency of emotion recognition, a new feature extraction method based on Superlets (SL) is developed in this paper. We designed an emotional experimental paradigm to induce positive, neutral and negative emotions. Further more, we extracted features using Superlets from the F7, F8, T7 and Pz electrode channels and classified three emotion states with SVM and DNN classifiers. In order to validate the performance of the proposed model, the collected EEG data set from our lab and SEED data set were used in this study. With SL features and DNN model, the average recognition accuracy from the 11 subjects was 85.75%, and the average recognition accuracy of SEED data set was 85.67%. The experiment results show that superlet transform could be used as a reliable feature extraction method in emotion recognition from EEG signal.

  PublisherDOI

• Isolation, identification, and proteomic analysis of outer membrane vesicles of Riemerella anatipestifer SX-1

  Poultry Science · 2024-03-11 · 3 citations

  articleOpen access

  Riemerella anatipestifer, belonging to Weeksellaceae Riemerella, is a bacterium that can infect ducks, geese, and turkeys, causing diseases known as duck infectious serositis, new duck disease, and duck septicemia. We collected diseased materials from ducks on a duck farm in China and then isolated and purified a strain of serotype 1 R. anatipestifer named SX-1. Animal experiments showed that SX-1 is a highly virulent strain with an LD50 value of 101 CFU/mL. The complete genome sequence was obtained. The complete genome sequence of R. anatipestifer SX-1 was 2,112,539 bp; 847 genes were involved in catalytic activity, and 445 genes were related to the cell membrane. The total length of the repetitive sequences was 8746 bp. Four CRISPR loci were predicted in R. anatipestifer strain SX-1, and four genomic islands were predicted. Concentration and ultra-high-speed centrifugation were used to extract the outer membrane vesicles of R. anatipestifer SX-1. The OMVs were extracted successfully. Particle size analysis revealed the size and abundance of particles: 147.4 nm, 94.9%; 293.6 nm, 1.1%; 327.2 nm, 1.1%; 397.2 nm, 0.3%; and 371.8 nm, 1.1%. The average size was 173.5 nm. Label-free proteomic technology was used to identify proteins in the outer membrane vesicles. ATCC 11845 served as the reference genome sequence, and 148 proteins were identified using proteomic analysis, which were classified into five categories based on their sources. Among them, 24 originated from cytoplasmic proteins, 4 from extracellular secreted proteins, 27 from outer membrane proteins, 10 from periplasmic proteins, and 83 from unknown sources. This study conducted a proteomic analysis of OMVs to provide a theoretical basis for the development of R. anatipestifer OMVs vaccines and adjuvants and lays the foundation for further research on the relationship between the pathogenicity of R. anatipestifer and OMVs.

  PublisherDOI

• Research on Helmet Detection Algorithm Based on Improved YOLOv5s

  Lecture notes in electrical engineering · 2023-01-01

  book-chapterSenior author
  PublisherDOI

• Aircraft Target Detection Algorithm Based on Improved YOLOv5s

  Lecture notes in electrical engineering · 2023-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

Recent grants

• CRI: Collaborative Research: Building the Next-Generation Global Routing Monitoring System

  NSF · $125k · 2006–2009

• NeTS-FIND Collaborative Research: Enabling Future Internet innovations through Transit wire (eFIT)

  NSF · $260k · 2007–2010

• FIA-NP: Collaborative Research: Named Data Networking Next Phase (NDN-NP)

  NSF · $2.3M · 2014–2018

• FIA: Collaborative Research: Named Data Networking (NDN)

  NSF · $2.3M · 2010–2015

• Collaborative Research: NeTS-NBD: Optimization and Games in Inter-domain Routing

  NSF · $120k · 2006–2007

Frequent coauthors

• Alexander Afanasyev

  Florida International University

  55 shared

• Beichuan Zhang

  University of Arizona

  53 shared

• Lan Wang

  44 shared

• Zhiyi Zhang

  Shanghai Maritime University

  31 shared

• Dan Massey

  University Hospital Heidelberg

  29 shared

• Songwu Lu

  27 shared

• Scott Shenker

  University of California, Berkeley

  22 shared

• Mohit Lad

  19 shared

Awards & honors

• Omidyar Network Award, 2023
• Internet Hall of Fame Member, 2021
• Lifetime Achievement Award for work on Communication Network…