Research group


Publications




[pdf]
Boundary Attributions Provide Normal (Vector) Explanations.
Zifan Wang, Matt Fredrikson, Anupam Datta
2021 Preprint.
[pdf]
Globally-Robust Neural Networks.
Klas Leino, Zifan Wang, Matt Fredrikson
2021 International Conference on Machine Learning (ICML).
[pdf]
Capture: Centralized Library Management for Heterogeneous IoT Devices.
Han Zhang, Abhijith Anilkumar, Matt Fredrikson, Yuvraj Agarwal
2021 Usenix Security Symposium.
[pdf]
Fast Geometric Projections for Local Robustness Certification.
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina Pasareanu
2021 International Conference on Learning Representations (ICLR) (spotlight).
[pdf]
Leave-one-out Unfairness.
Emily Black, Matt Fredrikson.
2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT).
[pdf]
Automating Audit with Policy Inference
Abhishek Bichhawat, Matt Fredrikson, Jean Yang
2021 Computer Security Foundations Symposium (CSF).
[pdf]
Netter: Probablistic, Stateful Network Models.
Han Zhang, Chi Zhang, Arthur Azevedo de Amorim, Yuvraj Agarwal, Matt Fredrikson, Limin Jia.
2021 International Conference on Verification, Model Checking, and Abstract Interpretation (VMCAI).
[pdf]
Smoothed Geometry for Robust Attribution.
Zifan Wang, Haofan Wang, Shakul Ramkumar, Matt Fredrikson, Piotr Mardziel, Anupam Datta
2020 Neural Information Processing Systems (NeurIPS).
[pdf]
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference.
Klas Leino, Matt Fredrikson.
2020 Usenix Security Symposium.
[pdf]
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness.
Samuel Yeom, Matt Fredrikson.
2020 International Joint Conference on Artificial Intelligence (IJCAI).
[pdf]
Learning Fair Representations for Kernel Models.
Zilong Tan, Samuel Yeom, Matt Fredrikson, Ameet Talwalkar
2020 International Conference on Artificial Intelligence and Statistics (AISTATS).
[pdf]
Reconciling Noninterference and Gradual Typing.
Arthur Azevedo de Amorim, Matt Fredrikson, Limin Jia.
2020 ACM/IEEE Symposium on Logic in Computer Science (LICS).
[pdf]
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models.
Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fredrikson, Anupam Datta.
2020 Meeting of the Association for Computational Linguistics (ACL).
[pdf]
Contextual and Granular Policy Enforcement in Database-Backed Applications.
Abhishek Bichhawat, Akash Trehan, Jean Yang, Matt Fredrikson
2020 ACM ASIA Conference on Computer and Communications Security (AsiaCCS)
[pdf]
Interpreting Interpretations: Organizing Attribution Methods by Criteria.
Zifan Wang, Piotr Mardziel, Anupam Datta, Matt Fredrikson
2020 CVPR Workshop on Fair, Data Efficient, and Trusted Computer Vision.
[pdf]
Overfitting, Robustness, and Malicious Algorithms: A study of potential causes of privacy risk in machine learning.
Samuel Yeom, Irene Giacomelli, Alan Menaged, Matt Fredrikson, Somesh Jha
Journal of Computer Security 28(1): 35-70 (2020)
[pdf]
FlipTest: Fairness Auditing via Optimal Transport.
Emily Black, Samuel Yeom, Matt Fredrikson.
2020 ACM Conference on Fairness, Accountability, and Transparency (FAT*).
[pdf]
"Why Are They Collecting My Data?": Inferring the Purposes of Network Traffic in Mobile Apps.
Haojian Jin, Minyi Liu, Kevan Dohia, Yuanchun Li, Gaurav Srivastava, Matt Fredrikson, Yuvraj Agarwal and J. Hong.
2019 ACM Transactions on Interactive, Mobile, Wearable Ubiquitous Technology (IMWUT/Ubicomp).
[pdf]
Feature-wise Bias Amplification.
Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta
2019 International Conference on Learning Representations (ICLR).
[pdf]
Hunting for Discriminatory Proxies in Linear Regression Models.
Samuel Yeom, Anupam Datta, Matt Fredrikson
2018 Conference on Neural Information Processing (NeurIPS).
[pdf]
Influence-Directed Explanations for Deep Convolutional Networks.
Klas Leino, Linyi Li, Shayak Sen, Anupam Datta, Matt Fredrikson
2018 Proceedings of the IEEE International Test Conference.
[pdf]
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting.
Samuel Yeom, Irene Giacomelli, Matt Fredrikson, Somesh Jha
2018 IEEE Computer Security Foundations Symposium (CSF).
(Distinguished Paper Award)
[pdf]
Supervising Feature Influence.
Shayak Sen, Piotr Mardziel, Anupam Datta, Matt Fredrikson
2018 Preprint
[pdf]
Proxy Non-Discrimination in Data-Driven Systems.
Anupam Datta, Matt Fredrikson, Gihyuk Ko, Piotr Mardziel, Shayak Sen
2017 Preprint
[pdf]
Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs.
Anupam Datta, Matt Fredrikson, Gihyuk Ko, Piotr Mardziel, Shayak Sen
2017 ACM Conference on Computer and Communications Security (CCS).
[pdf]
PrivacyProxy: Leveraging Crowdsourcing and In Situ Traffic Analysis to Detect and Mitigate Information Leakage.
Gaurav Srivastava, Saksham Chitkara, Kunal Ku, Swarup Kumar Sahoo, Matt Fredrikson, Jason Hong, Yuvraj Agarwal
2017 Preprint
[pdf]
PrivacyStreams: Enabling Transparency in Personal Data Processing for Mobile Apps.
Yuanchun Li, Fanglin Chen, Toby Jia-Jun Li, Yao Guo, Gang Huang, Matt Fredrikson, Yuvraj Agarwal, Jason Hong
2017 ACM Transactions on Interactive, Mobile, Wearable Ubiquitous Technology (IMWUT/Ubicomp).
[pdf]
Verifying and Synthesizing Constant-Resource Implementations with Types
Van Chan Ngo, M. Dehesa-Azuara, Matt Fredrikson, Jan Hoffmann
2017 IEEE Symposium on Security & Privacy (Oakland).
[pdf]
A Methodology for Formalizing Model-Inversion Attacks.
Xifan Wu, Matt Fredrikson, Somesh Jha, and Jeff Naughton.
2016 IEEE Computer Security Foundations Symposium (CSF).
[pdf]
The Limitations of Deep Learning in Adversarial Settings.
N. Papernot, P. McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, A. Swami.
2016 IEEE European Symposium on Security & Privacy (EuroSP).
[pdf]
Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences.
Xi Wu, Matt Fredrikson, W. Wu, Somesh Jha, and Jeff Naughton.
2015 Preprint
[pdf]
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures.
Matt Fredrikson, Somesh Jha, Tom Ristenpart
2015 ACM Conference on Computer and Communications Security (CCS).
[pdf]
Surreptitiously Weakening Cryptographic Systems
Bruce Schneier, Matt Fredrikson, Yoshi Kohno, Tom Ristenpart.
Cryptology ePrint Archive, Report 2015/097, February 2015.
[pdf]
Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing.
Matt Fredrikson, Eric Lantz, Somesh Jha, Simon M. Lin, C. David Page, Tom Ristenpart
2014 Usenix Security Symposium.
(Best Paper Award)
[pdf]
Z0: An Optimizing Distributing Zero-Knowledge Compiler.
Matt Fredrikson, Ben Livshits
2014 Usenix Security Symposium.
[pdf]
On the Practical Exploitability of Dual EC in TLS Implementations.
Stephen Checkoway, Matt Fredrikson, Ruben Niederhagen, Matthew Green, Tanja Lange, Tom Ristenpart, D. J. Bernstein, Jacob Maskiewicz, Hovav Shacham
2014 Usenix Security Symposium.
[pdf]
MoRePriv: Mobile OS Support for Application Personalization and Privacy.
Drew Davidson, Matt Fredrikson, Ben Livshits
2014 Annual Computer Security Applications Conference (ACSAC).
[pdf]
Satisfiability Modulo Counting: A New Approach for Analyzing Privacy Properties.
Matt Fredrikson, Somesh Jha
2014 Joint Meeting of Computer Science Logic and Logic in Computer Science (CSL-LICS).
[pdf]
Efficient Runtime Policy Enforcement Using Counterexample-Guided Abstraction Refinement.
Matt Fredrikson, Richard Joiner, Somesh Jha, Thomas Reps, Phillip Porras, Hassen Saidi, and Vinod Yegneswaran
Computer Aided Verification 2012 (CAV).
[pdf]
Towards Enforceable Data-Driven Privacy Policies.
Matt Fredrikson, Drew Davidson, Somesh Jha, Ben Livshits
2011 Workshop on Web 2.0 Security and Privacy (W2SP).
[pdf]
Dynamic Behavior Matching: A Complexity Analysis and New Approximation Algorithms.
Matt Fredrikson, Mihai Christodorescu, Somesh Jha.
2011 Conference on Automated Deduction (CADE).
[pdf]
RePriv: Re-Envisioning In-Browser Privacy.
Matt Fredrikson, Ben Livshits.
2011 IEEE Symposium on Security & Privacy (Oakland).
[pdf]
Verified Security for Browser Extensions.
A. Guha, Matt Fredrikson, N. Swamy, Ben Livshits.
2011 IEEE Symposium on Security & Privacy (Oakland).
[doi]
End-to-End Software Diversification of Internet Services.
Mihai Christodorescu, Matt Fredrikson, Somesh Jha, Jon Giffin
In Moving Target Defense, 2011, Springer New York.
[pdf]
Automatic Generation of Remediation Procedures for Malware Infections.
R. Paleari, L. Martignoni, E. Passerini, D. Davidson, Matt Fredrikson, J. Giffin, Somesh Jha.
2010 Usenix Security Symposium.
[pdf]
Synthesizing Near-Optimal Malware Specifications from Suspicious Behaviors.
Matt Fredrikson, Mihai Christodorescu, Somesh Jha, Reiner Sailer, Xifeng Yan.
2010 IEEE Symposium on Security & Privacy (Oakland).
[doi]
A Declarative Framework for Intrusion Analysis.
Matt Fredrikson, Mihai Christodorescu, Jon Giffin, Somesh Jha.
In Cyber-Situational Awareness, Editors: Sushil Jajodia, Peng Liu, Vipin Swarup, Clifford Wang. 2010, Springer New York.
[pdf]
Mining Graph Patterns Efficiently via Randomized Summaries.
C. Chen, C. X. Lin, Matt Fredrikson, Mihai Christodorescu, Xifeng Yan, Jiawei Han.
2009 Conference on Very Large Data Bases (VLDB).
[pdf]
A Layered Architecture for Detecting Malicious Behaviors.
L. Martignoni, E. Stinson, Matt Fredrikson, Somesh Jha, John Mitchell.
2008 Symposium on Recent Advances in Intrusion Detection (RAID).

Last updated 5/11/21