Nicholas Carlini

15.4k citations
34 papers · 1.8k · 3 hit papers · h-index 15

Impact in

    • Advanced Malware Detection Techniques
    • Adversarial Robustness in Machine Learning
    • Anomaly Detection Techniques and Applications
    • Privacy-Preserving Technologies in Data
    • Security and Verification in Computing
    • Domain Adaptation and Few-Shot Learning

Papers in

    • Adversarial Robustness in Machine Learning 14
    • Anomaly Detection Techniques and Applications 6
    • Domain Adaptation and Few-Shot Learning 4
    • Privacy-Preserving Technologies in Data 4
    • Cryptography and Data Security 3
    • Security and Verification in Computing 3
    • Topic Modeling 3
    • Advanced Malware Detection Techniques 8
Journals
arXiv (Cornell University) (2 papers)Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (1 paper)Neural Information Processing Systems (2 papers)USENIX Security Symposium (3 papers)Repository for Publications and Research Data (ETH Zurich) (1 paper)

In The Last Decade

Nicholas Carlini

29 papers receiving 1.7k citations

Nicholas Carlini's Hit Papers

Deduplicating Training Data Makes Language Models Better 2022 · 147 citations
1470+3+6Years since publication200400600

Peers

Nicholas Carlini
Comparison fields: 5 of 94
  • Signal Processing 566
  • Artificial Intelligence 1.6k
  • Health Informatics 37
  • Computer Vision and Pattern Recognition 357
  • Hardware and Architecture 107
Replace Amir Houmansadr with:
Amir Houmansadr United States
Yingqi Liu United States
Yuanshun Yao United States
Kevin Eykholt United States
Bolun Wang United States
Blaine Nelson United States
Hidayet Aksu United States
Daniel Lowd United States
Marco Barreno United States
Nicholas Carlini relative to Amir Houmansadr United States Amir Houmansadr's profile →
Citations per field
00.5×1.5×2.2×
Amir Houmansadr · 1×
Citations per year

Countries citing papers authored by Nicholas Carlini

Since Specialization
Citations

This map shows the geographic impact of Nicholas Carlini's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Nicholas Carlini with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Nicholas Carlini more than expected).

Fields of papers citing papers by Nicholas Carlini

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Nicholas Carlini. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Nicholas Carlini. The network helps show where Nicholas Carlini may publish in the future.

Co-authors

The 25 scholars most cited alongside Nicholas Carlini, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Nicholas Carlini Line = papers co-authored together Nicholas Carlini links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 34 papers — load more, or switch the sort, to bring in the rest.

#Work
1
Adversarial Examples Are Not Easily Detected
Hit paper breakdown →
2017608
2
Membership Inference Attacks From First Principles
Hit paper breakdown →
2022182
3
ROP is still dangerous: breaking modern defenses
2014168
4
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring
2020165
5
Hidden voice commands
2016161
6
Deduplicating Training Data Makes Language Models Better
Hit paper breakdown →
2022147
7
Adversarial Example Defense: Ensembles of Weak Defenses are not Strong
201794
8 202057
9
An evaluation of the Google Chrome extension security architecture
201242
10 202232
11
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
202028
12 202426
13
Adversarial Examples Are a Natural Consequence of Test Error in Noise
201922
14
Ground-Truth Adversarial Examples
201822
15 202121
16
High-Fidelity Extraction of Neural Network Models.
201912
17 202311
18
Measuring Robustness to Natural Distribution Shifts in Image Classification
202011
19
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
20208
20
Prototypical Examples in Deep Learning: Metrics, Characteristics, and Utility
20184

About Nicholas Carlini

Nicholas Carlini is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Information Systems and Computer Networks and Communications, having authored 34 papers that have together received 1.8k indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (14 papers), Advanced Malware Detection Techniques (8 papers), Anomaly Detection Techniques and Applications (6 papers), Domain Adaptation and Few-Shot Learning (4 papers), Privacy-Preserving Technologies in Data (4 papers), Cryptography and Data Security (3 papers), Security and Verification in Computing (3 papers) and Topic Modeling (3 papers). The work is most often cited by research in Signal Processing (566 citations), Artificial Intelligence (1.6k citations), Health Informatics (37 citations), Computer Vision and Pattern Recognition (357 citations) and Hardware and Architecture (107 citations). Nicholas Carlini has collaborated with scholars based in United States, Switzerland and United Kingdom. Frequent co-authors include David Wagner, Florian Tramèr, Andreas Terzis, Milad Nasr, Shuang Song, Steve Chien, David Berthelot, А.В. Куракин, Colin Raffel and Kihyuk Sohn. Their work appears in journals such as arXiv (Cornell University), Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, Neural Information Processing Systems, USENIX Security Symposium and Repository for Publications and Research Data (ETH Zurich).

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact