Matt Fredrikson

Matt Fredrikson

Carnegie Mellon University

H-index: 33

North America-United States

About Matt Fredrikson

Matt Fredrikson, With an exceptional h-index of 33 and a recent h-index of 29 (since 2020), a distinguished researcher at Carnegie Mellon University, specializes in the field of Security and Privacy, Fair & Trustworthy AI, Formal Methods.

His recent articles reflect a diverse array of research interests and contributions to the field:

Grounding Neural Inference with Satisfiability Modulo Theories

Representation engineering: A top-down approach to ai transparency

Centroid-Based Learning for Malware Detection and Novel Family Identification

Universal and transferable adversarial attacks on aligned language models

Effectively Leveraging Capacity for Improved Deterministic Robustness Certification

Enhancing Neural Network Transparency through Representation Analysis

Is Certifying Robustness Still Worthwhile?

Transfer Attacks and Defenses for Large Language Models on Coding Tasks

Matt Fredrikson Information

University

Position

Assistant Professor

Citations(all)

12405

Citations(since 2020)

10157

Cited By

5734

hIndex(all)

33

hIndex(since 2020)

29

i10Index(all)

49

i10Index(since 2020)

47

Email

University Profile Page

Carnegie Mellon University

Google Scholar

View Google Scholar Profile

Matt Fredrikson Skills & Research Interests

Security and Privacy

Fair & Trustworthy AI

Formal Methods

Top articles of Matt Fredrikson

Title

Journal

Author(s)

Publication Date

Grounding Neural Inference with Satisfiability Modulo Theories

Advances in Neural Information Processing Systems

Zifan Wang

Saranya Vijayakumar

Kaiji Lu

Vijay Ganesh

Somesh Jha

...

2024/2/13

Representation engineering: A top-down approach to ai transparency

arXiv preprint arXiv:2310.01405

Andy Zou

Long Phan

Sarah Chen

James Campbell

Phillip Guo

...

2023/10/2

Centroid-Based Learning for Malware Detection and Novel Family Identification

Saranya Vijayakumar

Zifan Wang

Yuhang Yao

Matt Fredrikson

2023/10/13

Universal and transferable adversarial attacks on aligned language models

arXiv preprint arXiv:2307.15043

Andy Zou

Zifan Wang

J Zico Kolter

Matt Fredrikson

2023/7/27

Effectively Leveraging Capacity for Improved Deterministic Robustness Certification

Kai Hu

Klas Leino

Zifan Wang

Matt Fredrikson

2023/10/13

Enhancing Neural Network Transparency through Representation Analysis

Andy Zou

Long Phan

Sarah Li Chen

James Campbell

Phillip Huang Guo

...

2023/10/13

Is Certifying Robustness Still Worthwhile?

arXiv preprint arXiv:2310.09361

Ravi Mangal

Klas Leino

Zifan Wang

Kai Hu

Weicheng Yu

...

2023/10/13

Transfer Attacks and Defenses for Large Language Models on Coding Tasks

arXiv preprint arXiv:2311.13445

Chi Zhang

Zifan Wang

Ravi Mangal

Matt Fredrikson

Limin Jia

...

2023/11/22

A recipe for improved certifiable robustness: Capacity and data

arXiv preprint arXiv:2310.02513

Kai Hu

Klas Leino

Zifan Wang

Matt Fredrikson

2023/10/4

Robustness Evaluation of Proxy Models against Adversarial Optimization

Andy Zou

Long Phan

Nathaniel Li

Jun Shern Chan

Mantas Mazeika

...

2023/10/13

Enhancing the insertion of NOP instructions to obfuscate malware via deep reinforcement learning

Computers & Security

Daniel Gibert

Matt Fredrikson

Carles Mateu

Jordi Planes

Quan Le

2022/2/1

Exploring Conceptual Soundness with TruLens

Anupam Datta

Matt Fredrikson

Klas Leino

Kaiji Lu

Shayak Sen

...

2022/7/20

TEO: Ephemeral ownership for iot devices to provide granular data control

Han Zhang

Yuvraj Agarwal

Matt Fredrikson

2022/6/27

On the Perils of Cascading Robust Classifiers

arXiv preprint arXiv:2206.00278

Ravi Mangal

Zifan Wang

Chi Zhang

Klas Leino

Corina Pasareanu

...

2022/6/1

Degradation Attacks on Certifiably Robust Neural Networks

Klas Leino

Chi Zhang

Ravi Mangal

Matt Fredrikson

Bryan Parno

...

2022/11/30

Faithful Explanations for Deep Graph Models

arXiv preprint arXiv:2205.11850

Zifan Wang

Yuhang Yao

Chaoran Zhang

Han Zhang

Youjie Kang

...

2022/5/24

Black-box audits for group distribution shifts

arXiv preprint arXiv:2209.03620

Marc Juárez

Samuel Yeom

Matt Fredrikson

2022/9/8

Privacy-preserving case-based explanations: Enabling visual interpretability by protecting privacy

IEEE Access

Helena Montenegro

Wilson Silva

Alex Gaudio

Matt Fredrikson

Asim Smailagic

...

2022/3/8

Self-correcting neural networks for safe classification

Klas Leino

Aymeric Fromherz

Ravi Mangal

Matt Fredrikson

Bryan Parno

...

2022/7/31

Capture: Centralized library management for heterogeneous {IoT} devices

Han Zhang

Abhijith Anilkumar

Matt Fredrikson

Yuvraj Agarwal

2021

See List of Professors in Matt Fredrikson University(Carnegie Mellon University)

Co-Authors

H-index: 95
John C Mitchell

John C Mitchell

Stanford University

H-index: 86
Somesh Jha

Somesh Jha

University of Wisconsin-Madison

H-index: 83
Jason Hong

Jason Hong

Carnegie Mellon University

H-index: 83
Thomas Reps

Thomas Reps

University of Wisconsin-Madison

H-index: 83
Patrick McDaniel

Patrick McDaniel

Penn State University

H-index: 66
Zico Kolter

Zico Kolter

Carnegie Mellon University

academic-engine