World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
63
Citations
19682
World Ranking
2713
National Ranking
1347

Research.com Recognitions

  • 2017 - Fellow of Alfred P. Sloan Foundation

Overview

Tom Goldstein is affiliated with the University of Maryland, College Park in the United States. Their research primarily spans the field of Computer Science, with substantial contributions in Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Signal Processing, and Computer Networks and Communications.

Within these fields, their work focuses on key topics including Adversarial Robustness in Machine Learning, Advanced Neural Network Applications, Anomaly Detection Techniques and Applications, Domain Adaptation and Few-Shot Learning, Topic Modeling, Natural Language Processing Techniques, and Machine Learning and Data Classification.

Goldstein has coauthored extensively with several researchers, including:

  • Micah Goldblum (81 coauthored works)
  • Jonas Geiping (50)
  • Liam Fowl (24)
  • Avi Schwarzschild (23)
  • John P. Dickerson (18)

Their frequent publication venues reflect their active engagement across prominent platforms:

  • arXiv (Cornell University) with 163 publications
  • Proceedings of the AAAI Conference on Artificial Intelligence with 4 publications
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) with 2 publications
  • Repository for Publications and Research Data (ETH Zurich) with 2 publications
  • IEEE Transactions on Pattern Analysis and Machine Intelligence with 1 publication

Goldstein's recent papers illustrate their research scope and interests:

  • "Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses," 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence
  • "A Cookbook of Self-Supervised Learning," 2023, arXiv (Cornell University)
  • "Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models," 2022, arXiv (Cornell University)
  • "A Watermark for Large Language Models," 2023, arXiv (Cornell University)
  • "SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training," 2021, arXiv (Cornell University)

They have been recognized by being named a Fellow of the Alfred P. Sloan Foundation in 2017.

Best Publications

  • The Split Bregman Method for L1-Regularized Problems

    Tom Goldstein;Stanley Osher

  • Visualizing the Loss Landscape of Neural Nets

    Hao Li;Zheng Xu;Gavin Taylor;Christoph Studer

  • Fast Alternating Direction Optimization Methods

    Tom Goldstein;Brendan O'Donoghue;Simon Setzer;Richard G. Baraniuk

  • Adversarial training for free

    Ali Shafahi;Mahyar Najibi;Mohammad Amin Ghiasi;Zheng Xu

  • Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction

    Tom Goldstein;Xavier Bresson;Stanley Osher

  • Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

    Ali Shafahi;W. Ronny Huang;Mahyar Najibi;Octavian Suciu

  • FreeLB: Enhanced Adversarial Training for Natural Language Understanding

    Chen Zhu;Yu Cheng;Zhe Gan;Siqi Sun

  • Quantized Precoding for Massive MU-MIMO

    Sven Jacobsson;Giuseppe Durisi;Mikael Coldrey;Tom Goldstein

  • PhaseMax: Convex Phase Retrieval via Basis Pursuit

    Tom Goldstein;Christoph Studer

  • A Watermark for Large Language Models

    Unknown

  • Adversarially Robust Distillation

    Micah Goldblum;Liam Fowl;Soheil Feizi;Tom Goldstein

  • A Field Guide to Forward-Backward Splitting with a FASTA Implementation

    Tom Goldstein;Christoph Studer;Richard G. Baraniuk

  • Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses.

    Micah Goldblum;Dimitris Tsipras;Chulin Xie;Xinyun Chen

  • DCAN: Dual Channel-Wise Alignment Networks for Unsupervised Scene Adaptation

    Zuxuan Wu;Xintong Han;Yen-Liang Lin;Mustafa Gökhan Uzunbas

  • A Cookbook of Self-Supervised Learning

    Unknown

  • Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

    Unknown

  • Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors

    Zuxuan Wu;Ser-Nam Lim;Larry S. Davis;Tom Goldstein

  • Training neural networks without gradients: a scalable ADMM approach

    Gavin Taylor;Ryan Burmeister;Zheng Xu;Bharat Singh

  • Channel Charting: Locating Users Within the Radio Environment Using Channel State Information

    Christoph Studer;Said Medjkouh;Emre Gonultas;Tom Goldstein

  • Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

    Unknown

  • Are adversarial examples inevitable

    Ali Shafahi;W. Ronny Huang;Christoph Studer;Soheil Feizi

  • Universal Adversarial Training

    Ali Shafahi;Mahyar Najibi;Zheng Xu;John P. Dickerson

  • Training Quantized Nets: A Deeper Understanding

    Hao Li;Soham De;Zheng Xu;Christoph Studer

  • Transferable Clean-Label Poisoning Attacks on Deep Neural Nets

    Chen Zhu;W. Ronny Huang;Ali Shafahi;Hengduo Li

  • Certified Data Removal from Machine Learning Models

    Chuan Guo;Tom Goldstein;Awni Hannun;Laurens van der Maaten

  • Certified Defenses for Adversarial Patches

    Ping-Yeh Chiang;Renkun Ni;Ahmed Abdelkader;Chen Zhu

Frequent Co-Authors

Giuseppe Durisi
Giuseppe Durisi Chalmers University of Technology
Richard G. Baraniuk
Richard G. Baraniuk Rice University
David W. Jacobs
David W. Jacobs University of Maryland, College Park
Larry S. Davis
Larry S. Davis University of Maryland, College Park
Zuxuan Wu
Zuxuan Wu Fudan University
Olav Tirkkonen
Olav Tirkkonen Aalto University
Mário A. T. Figueiredo
Mário A. T. Figueiredo Instituto Superior Técnico
Zhe Gan
Zhe Gan Microsoft (United States)
Joseph R. Cavallaro
Joseph R. Cavallaro Rice University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

If you’re exploring Computer Science in the USA, there are many easy certifications to get that can quickly boost your employability. These certifications often target practical skills in programming, networking, cybersecurity, or IT support, letting you enter the job market or advance in your current role with minimal downtime.

For those aiming for an advanced credential in less time, consider the shortest masters degree programs online. These accelerated options let you earn a respected qualification efficiently, helping you pivot careers or specialize without a long commitment.

When choosing a pathway, it’s worth looking at the most useful graduate degrees currently in demand. Data science, artificial intelligence, and cybersecurity are just some fields employers are actively seeking, offering promising growth and salary potential for graduates.

Lastly, online degrees aren’t limited to bachelor’s and master’s levels. Many students start with an associate degree online, providing foundational knowledge and faster entry into tech jobs, or a stepping stone to a four-year degree.

Best Scientists Citing Tom Goldstein

Trending Scientists