default search action
Matt Fredrikson
Matthew Fredrikson
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [c51]Kai Hu, Klas Leino, Zifan Wang, Matt Fredrikson:
A Recipe for Improved Certifiable Robustness. ICLR 2024 - [i44]Kai Hu, Weichen Yu, Tianjun Yao, Xiang Li, Wenhe Liu, Lijun Yu, Yining Li, Kai Chen, Zhiqiang Shen, Matt Fredrikson:
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization. CoRR abs/2405.09113 (2024) - [i43]Han Zhang, Zifan Wang, Mihir Dhamankar, Matt Fredrikson, Yuvraj Agarwal:
VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devices. CoRR abs/2406.00586 (2024) - [i42]Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, Rowan Wang, Zico Kolter, Matt Fredrikson, Dan Hendrycks:
Improving Alignment and Robustness with Circuit Breakers. CoRR abs/2406.04313 (2024) - [i41]Weiran Lin, Anna Gerchanovsky, Omer Akgul, Lujo Bauer, Matt Fredrikson, Zifan Wang:
Sales Whisperer: A Human-Inconspicuous Attack on LLM Brand Recommendations. CoRR abs/2406.04755 (2024) - 2023
- [c50]Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina S. Pasareanu, Matt Fredrikson:
On the Perils of Cascading Robust Classifiers. ICLR 2023 - [c49]Kai Hu, Andy Zou, Zifan Wang, Klas Leino, Matt Fredrikson:
Unlocking Deterministic Robustness Certification on ImageNet. NeurIPS 2023 - [c48]Zifan Wang, Saranya Vijayakumar, Kaiji Lu, Vijay Ganesh, Somesh Jha, Matt Fredrikson:
Grounding Neural Inference with Satisfiability Modulo Theories. NeurIPS 2023 - [i40]Matt Fredrikson, Kaiji Lu, Saranya Vijayakumar, Somesh Jha, Vijay Ganesh, Zifan Wang:
Learning Modulo Theories. CoRR abs/2301.11435 (2023) - [i39]Kai Hu, Andy Zou, Zifan Wang, Klas Leino, Matt Fredrikson
:
Scaling in Depth: Unlocking Robustness Certification on ImageNet. CoRR abs/2301.12549 (2023) - [i38]Andy Zou, Zifan Wang, J. Zico Kolter, Matt Fredrikson
Universal and Transferable Adversarial Attacks on Aligned Language Models. CoRR abs/2307.15043 (2023) - [i37]Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson
Representation Engineering: A Top-Down Approach to AI Transparency. CoRR abs/2310.01405 (2023) - [i36]Kai Hu, Klas Leino, Zifan Wang, Matt Fredrikson
A Recipe for Improved Certifiable Robustness: Capacity and Data. CoRR abs/2310.02513 (2023) - [i35]Ravi Mangal, Klas Leino, Zifan Wang, Kai Hu, Weicheng Yu, Corina S. Pasareanu, Anupam Datta, Matt Fredrikson
Is Certifying 𝓁p Robustness Still Worthwhile? CoRR abs/2310.09361 (2023) - [i34]Chi Zhang, Zifan Wang, Ravi Mangal, Matt Fredrikson
Transfer Attacks and Defenses for Large Language Models on Coding Tasks. CoRR abs/2311.13445 (2023) - 2022
- [j7]Helena Montenegro
Privacy-Preserving Case-Based Explanations: Enabling Visual Interpretability by Protecting Privacy. IEEE Access 10: 28333-28347 (2022) - [j6]Daniel Gibert
Enhancing the insertion of NOP instructions to obfuscate malware via deep reinforcement learning. Comput. Secur. 113: 102543 (2022) - [j5]Klas Leino, Chi Zhang, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu:
Degradation Attacks on Certifiably Robust Neural Networks. Trans. Mach. Learn. Res. 2022 (2022) - [c47]Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson
Self-correcting Neural Networks for Safe Classification. NSV/FoMLAS@CAV 2022: 96-130 - [c46]Emily Black, Klas Leino, Matt Fredrikson:
Selective Ensembles for Consistent Predictions. ICLR 2022 - [c45]Emily Black, Zifan Wang, Matt Fredrikson:
Consistent Counterfactuals for Deep Models. ICLR 2022 - [c44]Zifan Wang, Matt Fredrikson, Anupam Datta:
Robust Models Are More Interpretable Because Attributions Look Normal. ICML 2022: 22625-22651 - [c43]Han Zhang, Yuvraj Agarwal, Matt Fredrikson
TEO: ephemeral ownership for IoT devices to provide granular data control. MobiSys 2022: 302-315 - [c42]Han Zhang, Yuvraj Agarwal, Matt Fredrikson
Protecting user data through ephemeral ownership of IoT devices. MobiSys 2022: 620-621 - [i33]Zifan Wang, Yuhang Yao, Chaoran Zhang, Han Zhang, Youjie Kang, Carlee Joe-Wong, Matt Fredrikson
Faithful Explanations for Deep Graph Models. CoRR abs/2205.11850 (2022) - [i32]Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina S. Pasareanu, Matt Fredrikson
On the Perils of Cascading Robust Classifiers. CoRR abs/2206.00278 (2022) - [i31]Marc Juarez, Samuel Yeom, Matt Fredrikson:
Black-Box Audits for Group Distribution Shifts. CoRR abs/2209.03620 (2022) - 2021
- [c41]Abhishek Bichhawat, Matt Fredrikson
Automating Audit with Policy Inference. CSF 2021: 1-16 - [c40]Emily Black
Leave-one-out Unfairness. FAccT 2021: 285-295 - [c39]Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu:
Fast Geometric Projections for Local Robustness Certification. ICLR 2021 - [c38]Klas Leino, Zifan Wang, Matt Fredrikson:
Globally-Robust Neural Networks. ICML 2021: 6212-6222 - [c37]Anupam Datta, Matt Fredrikson
Machine Learning Explainability and Robustness: Connected at the Hip. KDD 2021: 4035-4036 - [c36]Anupam Datta, Matt Fredrikson, Klas Leino, Kaiji Lu, Shayak Sen, Ricardo Shih, Zifan Wang:
Exploring Conceptual Soundness with TruLens. NeurIPS (Competition and Demos) 2021: 302-307 - [c35]Klas Leino, Matt Fredrikson:
Relaxing Local Robustness. NeurIPS 2021: 17072-17083 - [c34]Han Zhang, Abhijith Anilkumar, Matt Fredrikson, Yuvraj Agarwal:
Capture: Centralized Library Management for Heterogeneous IoT Devices. USENIX Security Symposium 2021: 4187-4204 - [c33]Han Zhang
Netter: Probabilistic, Stateful Network Models. VMCAI 2021: 486-508 - [i30]Klas Leino, Zifan Wang, Matt Fredrikson
Globally-Robust Neural Networks. CoRR abs/2102.08452 (2021) - [i29]Zifan Wang, Matt Fredrikson
Boundary Attributions Provide Normal (Vector) Explanations. CoRR abs/2103.11257 (2021) - [i28]Jason I. Hong, Yuvraj Agarwal, Matt Fredrikson
The Design of the User Interfaces for Privacy Enhancements for Android. CoRR abs/2104.12032 (2021) - [i27]Klas Leino, Matt Fredrikson
Relaxing Local Robustness. CoRR abs/2106.06624 (2021) - [i26]Emily Black, Matt Fredrikson:
Leave-one-out Unfairness. CoRR abs/2107.10171 (2021) - [i25]Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson
Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair. CoRR abs/2107.11445 (2021) - [i24]Emily Black, Zifan Wang, Matt Fredrikson
Consistent Counterfactuals for Deep Models. CoRR abs/2110.03109 (2021) - [i23]Emily Black, Klas Leino, Matt Fredrikson
Selective Ensembles for Consistent Predictions. CoRR abs/2111.08230 (2021) - [i22]Daniel Gibert, Matt Fredrikson
Enhancing the Insertion of NOP Instructions to Obfuscate Malware via Deep Reinforcement Learning. CoRR abs/2111.09626 (2021) - 2020
- [j4]Samuel Yeom, Irene Giacomelli, Alan Menaged, Matt Fredrikson
Overfitting, robustness, and malicious algorithms: A study of potential causes of privacy risk in machine learning. J. Comput. Secur. 28(1): 35-70 (2020) - [c32]Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fredrikson
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models. ACL 2020: 4748-4757 - [c31]Zilong Tan, Samuel Yeom, Matt Fredrikson, Ameet Talwalkar:
Learning Fair Representations for Kernel Models. AISTATS 2020: 155-166 - [c30]Abhishek Bichhawat, Matt Fredrikson
Contextual and Granular Policy Enforcement in Database-backed Applications. AsiaCCS 2020: 432-444 - [c29]Zifan Wang, Piotr Mardziel, Anupam Datta, Matt Fredrikson
Interpreting Interpretations: Organizing Attribution Methods by Criteria. CVPR Workshops 2020: 48-55 - [c28]Emily Black
FlipTest: fairness testing via optimal transport. FAT* 2020: 111-121 - [c27]Samuel Yeom, Matt Fredrikson
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness. IJCAI 2020: 437-443 - [c26]Arthur Azevedo de Amorim, Matt Fredrikson
Reconciling noninterference and gradual typing. LICS 2020: 116-129 - [c25]Zifan Wang, Haofan Wang, Shakul Ramkumar, Piotr Mardziel, Matt Fredrikson, Anupam Datta:
Smoothed Geometry for Robust Attribution. NeurIPS 2020 - [c24]Klas Leino, Matt Fredrikson:
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference. USENIX Security Symposium 2020: 1605-1622 - [i21]Aymeric Fromherz, Klas Leino, Matt Fredrikson
Fast Geometric Projections for Local Robustness Certification. CoRR abs/2002.04742 (2020) - [i20]Samuel Yeom, Matt Fredrikson:
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness. CoRR abs/2002.07738 (2020) - [i19]Zifan Wang, Piotr Mardziel, Anupam Datta, Matt Fredrikson
Interpreting Interpretations: Organizing Attribution Methods by Criteria. CoRR abs/2002.07985 (2020) - [i18]Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fredrikson, Anupam Datta:
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models. CoRR abs/2005.01190 (2020) - [i17]Zifan Wang, Haofan Wang, Shakul Ramkumar, Matt Fredrikson
Smoothed Geometry for Robust Attribution. CoRR abs/2006.06643 (2020)
2010 – 2019
- 2019
- [c23]Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta:
Feature-Wise Bias Amplification. ICLR (Poster) 2019 - [i16]Emily Black, Samuel Yeom, Matt Fredrikson
FlipTest: Fairness Auditing via Optimal Transport. CoRR abs/1906.09218 (2019) - [i15]Klas Leino, Matt Fredrikson
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference. CoRR abs/1906.11798 (2019) - [i14]Zilong Tan, Samuel Yeom, Matt Fredrikson
Learning Fair Representations for Kernel Models. CoRR abs/1906.11813 (2019) - 2018
- [j3]Haojian Jin, Minyi Liu, Kevan Dodhia, Yuanchun Li, Gaurav Srivastava, Matthew Fredrikson
Why Are They Collecting My Data?: Inferring the Purposes of Network Traffic in Mobile Apps. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2(4): 173:1-173:27 (2018) - [c22]Samuel Yeom, Irene Giacomelli, Matt Fredrikson
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting. CSF 2018: 268-282 - [c21]Ryan Wagner, David Garlan, Matt Fredrikson
Quantitative underpinnings of secure, graceful degradation: poster. HotSoS 2018: 25:1 - [c20]Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson
Influence-Directed Explanations for Deep Convolutional Networks. ITC 2018: 1-8 - [c19]Samuel Yeom, Anupam Datta, Matt Fredrikson:
Hunting for Discriminatory Proxies in Linear Regression Models. NeurIPS 2018: 4573-4583 - [i13]Van Chan Ngo, Mario Dehesa-Azuara, Matthew Fredrikson
Verifying and Synthesizing Constant-Resource Implementations with Types. CoRR abs/1801.01896 (2018) - [i12]Klas Leino, Linyi Li, Shayak Sen, Anupam Datta, Matt Fredrikson
Influence-Directed Explanations for Deep Convolutional Networks. CoRR abs/1802.03788 (2018) - [i11]Shayak Sen, Piotr Mardziel, Anupam Datta, Matthew Fredrikson
Supervising Feature Influence. CoRR abs/1803.10815 (2018) - [i10]Samuel Yeom, Anupam Datta, Matt Fredrikson
Hunting for Discriminatory Proxies in Linear Regression Models. CoRR abs/1810.07155 (2018) - [i9]Abhishek Bichhawat, Akash Trehan, Jean Yang, Matt Fredrikson
ESTRELA: Automated Policy Enforcement Across Remote APIs. CoRR abs/1811.08234 (2018) - [i8]Klas Leino, Matt Fredrikson
Feature-Wise Bias Amplification. CoRR abs/1812.08999 (2018) - 2017
- [j2]Yuanchun Li, Fanglin Chen, Toby Jia-Jun Li
PrivacyStreams: Enabling Transparency in Personal Data Processing for Mobile Apps. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 1(3): 76:1-76:26 (2017) - [c18]Anupam Datta, Matthew Fredrikson
Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs. CCS 2017: 1193-1210 - [c17]Van Chan Ngo
Verifying and Synthesizing Constant-Resource Implementations with Types. IEEE Symposium on Security and Privacy 2017: 710-728 - [i7]Anupam Datta, Matthew Fredrikson
Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs. CoRR abs/1705.07807 (2017) - [i6]Anupam Datta, Matt Fredrikson
Proxy Non-Discrimination in Data-Driven Systems. CoRR abs/1707.08120 (2017) - [i5]Gaurav Srivastava, Saksham Chitkara, Kevin Ku, Swarup Kumar Sahoo, Matt Fredrikson, Jason I. Hong, Yuvraj Agarwal:
PrivacyProxy: Leveraging Crowdsourcing and In Situ Traffic Analysis to Detect and Mitigate Information Leakage. CoRR abs/1708.06384 (2017) - [i4]Samuel Yeom, Matt Fredrikson
The Unintended Consequences of Overfitting: Training Data Inference Attacks. CoRR abs/1709.01604 (2017) - 2016
- [c16]Xi Wu, Matthew Fredrikson
A Methodology for Formalizing Model-Inversion Attacks. CSF 2016: 355-370 - [c15]Nicolas Papernot, Patrick D. McDaniel, Somesh Jha, Matt Fredrikson
The Limitations of Deep Learning in Adversarial Settings. EuroS&P 2016: 372-387 - 2015
- [c14]Matt Fredrikson
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures. CCS 2015: 1322-1333 - [i3]Nicolas Papernot, Patrick D. McDaniel, Somesh Jha, Matt Fredrikson
The Limitations of Deep Learning in Adversarial Settings. CoRR abs/1511.07528 (2015) - [i2]Xi Wu, Matthew Fredrikson
Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences. CoRR abs/1512.06388 (2015) - [i1]Bruce Schneier, Matthew Fredrikson, Tadayoshi Kohno, Thomas Ristenpart:
Surreptitiously Weakening Cryptographic Systems. IACR Cryptol. ePrint Arch. 2015: 97 (2015) - 2014
- [c13]Drew Davidson, Matt Fredrikson
MoRePriv: mobile OS support for application personalization and privacy. ACSAC 2014: 236-245 - [c12]Matthew Fredrikson
Satisfiability modulo counting: a new approach for analyzing privacy properties. CSL-LICS 2014: 42:1-42:10 - [c11]Matthew Fredrikson, Eric Lantz, Somesh Jha, Simon M. Lin, David Page, Thomas Ristenpart:
Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing. USENIX Security Symposium 2014: 17-32 - [c10]Stephen Checkoway, Ruben Niederhagen, Adam Everspaugh, Matthew Green, Tanja Lange, Thomas Ristenpart, Daniel J. Bernstein, Jake Maskiewicz, Hovav Shacham, Matthew Fredrikson:
On the Practical Exploitability of Dual EC in TLS Implementations. USENIX Security Symposium 2014: 319-335 - [c9]Matthew Fredrikson, Benjamin Livshits:
ZØ: An Optimizing Distributing Zero-Knowledge Compiler. USENIX Security Symposium 2014: 909-924 - 2013
- [c8]Somesh Jha, Matthew Fredrikson
Synthesizing near-optimal malware specifications from suspicious behaviors. MALWARE 2013: 41-50 - 2012
- [c7]Matthew Fredrikson
Efficient Runtime Policy Enforcement Using Counterexample-Guided Abstraction Refinement. CAV 2012: 548-563 - 2011
- [c6]Matthew Fredrikson
Dynamic Behavior Matching: A Complexity Analysis and New Approximation Algorithms. CADE 2011: 252-267 - [c5]Arjun Guha, Matthew Fredrikson
Verified Security for Browser Extensions. IEEE Symposium on Security and Privacy 2011: 115-130 - [c4]Matthew Fredrikson
RePriv: Re-imagining Content Personalization and In-browser Privacy. IEEE Symposium on Security and Privacy 2011: 131-146 - [p4]Mihai Christodorescu, Matthew Fredrikson
End-to-End Software Diversification of Internet Services. Moving Target Defense 2011: 117-130 - 2010
- [c3]Matt Fredrikson
Synthesizing Near-Optimal Malware Specifications from Suspicious Behaviors. IEEE Symposium on Security and Privacy 2010: 45-60 - [c2]Roberto Paleari, Lorenzo Martignoni, Emanuele Passerini, Drew Davidson, Matt Fredrikson, Jonathon T. Giffin, Somesh Jha:
Automatic Generation of Remediation Procedures for Malware Infections. USENIX Security Symposium 2010: 419-434 - [p3]Chen Chen, Cindy Xide Lin, Matt Fredrikson
Mining Large Information Networks by Graph Summarization. Link Mining 2010: 475-501 - [p2]Paul Barford, Marc Dacier
Cyber SA: Situational Awareness for Cyber Defense. Cyber Situational Awareness 2010: 3-13 - [p1]Matt Fredrikson
A Declarative Framework for Intrusion Analysis. Cyber Situational Awareness 2010: 179-200
2000 – 2009
- 2009
- [j1]Chen Chen, Cindy Xide Lin, Matt Fredrikson
Mining Graph Patterns Efficiently via Randomized Summaries. Proc. VLDB Endow. 2(1): 742-753 (2009) - 2008
- [c1]Lorenzo Martignoni, Elizabeth Stinson, Matt Fredrikson
A Layered Architecture for Detecting Malicious Behaviors. RAID 2008: 78-97
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-09 21:30 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: