World's Best Scientists 2026 revealed!
Award Badge
Rising Stars
2025

D-Index & Metrics

Rising Stars

D-Index
53
Citations
30328
World Ranking
238
National Ranking
36

Computer Science

D-Index
54
Citations
28199
World Ranking
4429
National Ranking
2071

Research.com Recognitions

  • 2025 - Research.com Rising Stars Award

Overview

Nicholas Carlini is affiliated with Google in the United States and has a research focus centered on computer science. Their work spans several subfields including artificial intelligence, computer vision and pattern recognition, signal processing, radiology, nuclear medicine and imaging, as well as computer networks and communications.

The scientist's research primarily addresses topics such as adversarial robustness in machine learning, privacy-preserving technologies in data, topic modeling, anomaly detection techniques and applications, advanced malware detection techniques, cryptography and data security, and natural language processing techniques.

Among the recently published papers by Nicholas Carlini are: "Membership Inference Attacks From First Principles" (2022) presented at the 2022 IEEE Symposium on Security and Privacy (SP); "Extracting Training Data from Large Language Models" (2020) published on arXiv (Cornell University). Other notable papers connected through coauthors include "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence" (2020) from arXiv (Cornell University) and "Deduplicating Training Data Makes Language Models Better" (2022) published in the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), reflecting collaborative research efforts.

Frequent coauthors collaborating with Nicholas Carlini include Florian Tramèr, Milad Nasr, Matthew Jagielski, Daphne Ippolito, and Katherine Lee.

Publication venues where Nicholas Carlini has contributed include: arXiv (Cornell University), the 2022 IEEE Symposium on Security and Privacy (SP), the Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), the Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, and Foundations and Trends® in Privacy and Security.

Best Publications

  • Towards Evaluating the Robustness of Neural Networks

    Nicholas Carlini;David Wagner

  • FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

    Kihyuk Sohn;David Berthelot;Chun-Liang Li;Zizhao Zhang

  • Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

    Anish Athalye;Nicholas Carlini;David A. Wagner

  • MixMatch: A Holistic Approach to Semi-Supervised Learning

    David Berthelot;Nicholas Carlini;Ian Goodfellow;Nicolas Papernot

  • Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods

    Nicholas Carlini;David Wagner

  • Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

    Nicholas Carlini;David Wagner

  • On Evaluating Adversarial Robustness

    Nicholas Carlini;Anish Athalye;Nicolas Papernot;Wieland Brendel

  • Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

    Nicolas Papernot;Fartash Faghri;Nicholas Carlini;Ian Goodfellow

  • Membership Inference Attacks From First Principles

    Unknown

  • The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks

    Nicholas Carlini;Chang Liu;Úlfar Erlingsson;Jernej Kos

  • Hidden voice commands

    Nicholas Carlini;Pratyush Mishra;Tavish Vaidya;Yuankai Zhang

  • On Adaptive Attacks to Adversarial Example Defenses

    Florian Tramer;Nicholas Carlini;Wieland Brendel;Aleksander Madry

  • ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

    David Berthelot;Nicholas Carlini;Ekin D. Cubuk;Alex Kurakin

  • ROP is still dangerous: breaking modern defenses

    Nicholas Carlini;David Wagner

  • Extracting Training Data from Large Language Models

    Nicholas Carlini;Florian Tramèr;Eric Wallace;Matthew Jagielski

  • Defensive Distillation is Not Robust to Adversarial Examples

    Nicholas Carlini;David A. Wagner

  • Adversarial Example Defense: Ensembles of Weak Defenses are not Strong

    Warren He;James Wei;Xinyun Chen;Nicholas Carlini

  • Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition.

    Yao Qin;Nicholas Carlini;Garrison W. Cottrell;Ian J. Goodfellow

  • Measuring Robustness to Natural Distribution Shifts in Image Classification

    Rohan Taori;Achal Dave;Vaishaal Shankar;Nicholas Carlini

  • Deduplicating Training Data Makes Language Models Better

    Katherine Lee;Daphne Ippolito;Andrew Nystrom;Chiyuan Zhang

  • ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

    David Berthelot;Nicholas Carlini;Ekin D. Cubuk;Alex Kurakin

  • Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition

    Yao Qin;Nicholas Carlini;Ian Goodfellow;Garrison Cottrell

  • Adversarial Examples Are a Natural Consequence of Test Error in Noise

    Justin Gilmer;Nicolas Ford;Nicholas Carlini;Ekin D. Cubuk

Frequent Co-Authors

David Wagner
David Wagner University of California, Berkeley
Nicolas Papernot
Nicolas Papernot University of Toronto
Colin Raffel
Colin Raffel University of Toronto
Dawn Song
Dawn Song University of California, Berkeley
Ian Goodfellow
Ian Goodfellow Google (United States)
Ekin D. Cubuk
Ekin D. Cubuk Google (United States)
Kihyuk Sohn
Kihyuk Sohn Google (United States)
Benjamin Recht
Benjamin Recht University of California, Berkeley

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

Exploring computer science in the USA often sparks interest in other rapidly growing fields. If you are looking to expand your skillset or branch into a specialized area, consider flexible online degree options that align with unique career goals.

For those interested in public safety, an affordable option is the cheapest online master's degree in criminal justice. This pathway can open doors to roles in law enforcement, criminology, and legal analysis.

Business-minded individuals may prefer online accounting degrees. These programs provide essential financial skills that are highly transferable and in demand across industries.

If you have a strong interest in data, a data science master online can boost your expertise in analytics, machine learning, and big data. This is a top choice for those seeking advanced roles in technology and information management.

Finally, opportunities in the built environment can be accessed via the best 2 year construction management degree online. This accelerated program is ideal for future project leaders in construction and real estate.

Best Scientists Citing Nicholas Carlini

Trending Scientists