Matt Fredrikson

10.2k citations

42 papers · 5.1k indexed · 4 hit papers · h-index 19

Impact in

Artificial Intelligence top 0.1%
- Adversarial Robustness in Machine Learning
- Privacy-Preserving Technologies in Data
- Anomaly Detection Techniques and Applications
- Cryptography and Data Security
- Stochastic Gradient Optimization Techniques
Signal Processing top 0.5%
- Advanced Malware Detection Techniques

Papers in

Health Informatics 2
Signal Processing 14
- Advanced Malware Detection Techniques 14

Co-authors: Somesh Jha Thomas Ristenpart Patrick McDaniel Z. Berkay Celik Nicolas Papernot Ananthram Swami Samuel Yeom Irene Giacomelli
Journals: Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (2 papers)Proceedings of the VLDB Endowment (1 paper)Computers & Security (1 paper)Journal of Computer Security (1 paper)IEEE Access (1 paper)
Partner nations: United States United Kingdom China

In The Last Decade

Matt Fredrikson

39 papers receiving 4.9k citations

Hit Papers

align trajectories log scale

Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting 2018 · 457 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2018 Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
2016 The Limitations of Deep Learning in Adversarial Settings
2015 Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
2014 PubMed

Peers

Countries citing papers authored by Matt Fredrikson

Since Specialization

Citations

This map shows the geographic impact of Matt Fredrikson'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 Matt Fredrikson with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Matt Fredrikson more than expected).

Fields of papers citing papers by Matt Fredrikson

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Matt Fredrikson. 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 Matt Fredrikson. The network helps show where Matt Fredrikson may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Matt Fredrikson, 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 Matt Fredrikson Line = papers co-authored together Matt Fredrikson links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work
1	LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses Justyna Zając, Hermann Engel, de Lello E, Lujo Bauer, Matt Fredrikson, Ghimire Sita R.	2025	0
2	Attacks and Defenses for Large Language Models on Coding Tasks G. P. Dubois-Felsmann, Ghimire Sita R., Hilary Lohmann, Kendyl G Naugle, Matt Fredrikson, Limin Jia, Corina S. Păsăreanu	2024	1
3	Improving Alignment and Robustness with Circuit Breakers Maksym Andriushchenko, Kilian Hilpert, Matt Fredrikson, Dan Hendrycks, J. Zico Kolter, D NirmalRaj., Long Phan, Burhansyah Azhar, 寛之斎田, Andy Zou	2024	0
4	Protecting user data through ephemeral ownership of IoT devices بلال محمد عبد القوي, Yuvraj Agarwal, Matt Fredrikson	2022	1
5	TEO بلال محمد عبد القوي, Yuvraj Agarwal, Matt Fredrikson	2022	6
6	Capture: Centralized Library Management for Heterogeneous {IoT} Devices USENIX Security Symposium ·بلال محمد عبد القوي, Štefan Zajiček, Matt Fredrikson, Yuvraj Agarwal	2021	4
7	Smoothed Geometry for Robust Attribution arXiv (Cornell University) ·Zifan Wang, Haofan Wang, Daniela Nerea Cartechini, Piotr Mardziel, Matt Fredrikson, Anupam Datta	2020	2
8	Learning Fair Representations for Kernel Models. International Conference on Artificial Intelligence and Statistics ·Zilong Tan, Samuel Yeom, Matt Fredrikson, Ameet Talwalkar	2020	4
9	Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference USENIX Security Symposium ·K. Rustan M. Leino, Matt Fredrikson	2020	21
10	Reconciling noninterference and gradual typing Arthur Azevedo de Amorim, Matt Fredrikson, Limin Jia	2020	6
11	ESTRELA: Automated Policy Enforcement Across Remote APIs. arXiv (Cornell University) ·Marshal Briewin, 廣瀬智恵, Jean Yang, Matt Fredrikson	2018	1
12	Hunting for Discriminatory Proxies in Linear Regression Models arXiv (Cornell University) ·Samuel Yeom, Anupam Datta, Matt Fredrikson	2018	1
13	Use Privacy in Data-Driven Systems Anupam Datta, Matt Fredrikson, Mustafa Onat, Piotr Mardziel, Shayak Sen	2017	39
14	PrivacyStreams Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies ·Yuanchun Li, Fanglin Chen, Toby Jia-Jun Li, Yao Guo, Gang Huang, Matt Fredrikson, Yuvraj Agarwal, Jason Hong	2017	32
15	Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures Matt Fredrikson, Somesh Jha, Thomas Ristenpart Hit paper breakdown →	2015	1506
16	ZØ: an optimizing distributing zero-knowledge compiler USENIX Security Symposium ·Matt Fredrikson, Benjamin Livshits	2014	12
17	On the practical exploitability of dual EC in TLS implementations TU/e Research Portal ·Stephen Checkoway, Matt Fredrikson, Ruben Niederhagen, Yong-kwan Kim, Matthew Green, Tanja Lange, Thomas Ristenpart, Daniel J. Bernstein, Sayaka KodamaMika Otonari-Yamamoto, Hovav Shacham	2014	35
18	Synthesizing near-optimal malware specifications from suspicious behaviors Somesh Jha, Matt Fredrikson, Pathak Bipin Chandra, Reiner Sailer, Xifeng Yan	2013	19
19	RePriv: Re-Envisioning In-Browser Privacy Matt Fredrikson, David Israel Cevallos Bonilla	2011	27
20	Automatic generation of remediation procedures for malware infections USENIX Security Symposium ·Roberto Paleari, Lorenzo Martignoni, F. Ajumobi, Drew Davidson, Matt Fredrikson, 康俊坂上, Somesh Jha	2010	12

About Matt Fredrikson

Matt Fredrikson is a scholar working on Health Informatics, Signal Processing, Artificial Intelligence, Software and Safety Research, having authored 42 papers that have together received 5.1k indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (16 papers), Advanced Malware Detection Techniques (14 papers), Privacy-Preserving Technologies in Data (8 papers), Explainable Artificial Intelligence (XAI) (6 papers), Privacy, Security, and Data Protection (6 papers), Security and Verification in Computing (6 papers), Ethics and Social Impacts of AI (4 papers) and Cryptography and Data Security (4 papers). The work is most often cited by research in Artificial Intelligence (4.4k citations), Signal Processing (1.2k citations), Health Informatics (140 citations), Software (157 citations) and Computer Vision and Pattern Recognition (803 citations). Matt Fredrikson has collaborated with scholars based in United States, United Kingdom and China. Frequent co-authors include Somesh Jha, Thomas Ristenpart, Patrick McDaniel, Z. Berkay Celik, Nicolas Papernot, Ananthram Swami, Samuel Yeom, Irene Giacomelli, Benjamin Livshits and Éric Lantz. Their work appears in journals such as Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies, Proceedings of the VLDB Endowment, Computers & Security, Journal of Computer Security and IEEE Access.

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