Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Influence patterns for explaining information flow in BERT
NIPS '21: Proceedings of the 35th International Conference on Neural Information Processing SystemsArticle No.: 341, Pages 4461–4474While "attention is all you need" may be proving true, we do not know why: attention-based transformer models such as BERT are superior but how information flows from input tokens to output predictions are unclear. We introduce influence patterns, ...
- research-articleOctober 2021
Fairness Under Feature Exemptions: Counterfactual and Observational Measures
IEEE Transactions on Information Theory (ITHR), Volume 67, Issue 10Pages 6675–6710https://doi.org/10.1109/TIT.2021.3103206With the growing use of machine learning algorithms in highly consequential domains, the quantification and removal of disparity in decision making with respect to protected attributes, such as gender, race, etc., is becoming increasingly important. While ...
- abstractAugust 2021
Machine Learning Explainability and Robustness: Connected at the Hip
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningPages 4035–4036https://doi.org/10.1145/3447548.3470806This tutorial examines the synergistic relationship between explainability methods for machine learning and a significant problem related to model quality: robustness against adversarial perturbations. We begin with a broad overview of approaches to ...
- doctoral_thesisJanuary 2021
Strategies for Fair, Explainable, and Reliable Machine Learning Using Information Theory
AbstractMachine learning is entering every aspect of our lives, including high-stakes applications that directly affect people's lives, such as, hiring, education, lending, or healthcare. While these machine learning models are undoubtedly great at ...
- research-articleDecember 2020
Smoothed geometry for robust attribution
NIPS '20: Proceedings of the 34th International Conference on Neural Information Processing SystemsArticle No.: 1143, Pages 13623–13634Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is especially ...
-
- ArticleDecember 2018
Hunting for discriminatory proxies in linear regression models
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsPages 4573–4583A machine learning model may exhibit discrimination when used to make decisions involving people. One potential cause for such outcomes is that the model uses a statistical proxy for a protected demographic attribute. In this paper we formulate a ...
- research-articleJune 2018
Device microagent for IoT home gateway: a lightweight plug-n-play architecture
Smart home implementation in IoT involves practical challenges of management and scalability of connecting various non IP end-devices i.e. sensors and actuators behind the connnected home gateway. While there are separate standards for interaction ...
- research-articleOctober 2017
Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs
CCS '17: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications SecurityPages 1193–1210https://doi.org/10.1145/3133956.3134097This paper presents an approach to formalizing and enforcing a class of use privacy properties in data-driven systems. In contrast to prior work, we focus on use restrictions on proxies (i.e. strong predictors) of protected information types. Our ...
- research-articleDecember 2016
Information flow for security in control systems
2016 IEEE 55th Conference on Decision and Control (CDC)Pages 5065–5072https://doi.org/10.1109/CDC.2016.7799044This paper considers the development of information flow analyses to support resilient design and active detection of adversaries in cyber physical systems (CPS). CPS security, though well studied, suffers from fragmentation. In this paper, we consider ...
- ArticleAugust 2016
Überspark: enforcing verifiable object abstractions for automated compositional security analysis of a hypervisor
We present überSpark (üSpark), an innovative architecture for compositional verification of security properties of extensible hypervisors written in C and Assembly. üSpark comprises two key ideas: (i) endowing low-level system software with abstractions ...
- reportAugust 2016
Report on the NSF Workshop on Formal Methods for Security
- Stephen Chong,
- Joshua Guttman,
- Anupam Datta,
- Andrew Myers,
- Benjamin Pierce,
- Patrick Schaumont,
- Tim Sherwood,
- Nickolai Zeldovich
The NSF workshop on Security and Formal Methods, held 19--20 November 2015, brought together developers of formal methods, researchers exploring how to apply formal methods to various kinds of systems, and people familiar with the security problem ...
- research-articleOctober 2015
Equivalence-based Security for Querying Encrypted Databases: Theory and Application to Privacy Policy Audits
CCS '15: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications SecurityPages 1130–1143https://doi.org/10.1145/2810103.2813638To reduce costs, organizations may outsource data storage and data processing to third-party clouds. This raises confidentiality concerns, since the outsourced data may have sensitive information. Although semantically secure encryption of the data ...
- ArticleJuly 2015
Influence in classification via cooperative game theory
A dataset has been classified by some unknown classifier into two types of points. What were the most important factors in determining the classification outcome? In this work, we employ an axiomatic approach in order to uniquely characterize an ...
- ArticleJuly 2015
Incentivizing peer grading in MOOCS: an audit game approach
In Massively Open Online Courses (MOOCs) TA resources are limited; most MOOCs use peer assessments to grade assignments. Students have to divide up their time between working on their own homework and grading others. If there is no risk of being caught ...
- ArticleJuly 2015
A Methodology for Information Flow Experiments
CSF '15: Proceedings of the 2015 IEEE 28th Computer Security Foundations SymposiumPages 554–568https://doi.org/10.1109/CSF.2015.40Information flow analysis has largely focused on methods that require access to the program in question or total control over an analyzed system. We consider the case where the analyst has neither control over nor a white-box model of the analyzed ...
- ArticleJuly 2015
A Logic of Programs with Interface-Confined Code
CSF '15: Proceedings of the 2015 IEEE 28th Computer Security Foundations SymposiumPages 512–525https://doi.org/10.1109/CSF.2015.38Interface-confinement is a common mechanism that secures untrusted code by executing it inside a sandbox. The sandbox limits (confines) the code's interaction with key system resources to a restricted set of interfaces. This practice is seen in web ...
- ArticleJuly 2015
Program Actions as Actual Causes: A Building Block for Accountability
CSF '15: Proceedings of the 2015 IEEE 28th Computer Security Foundations SymposiumPages 261–275https://doi.org/10.1109/CSF.2015.25Protocols for tasks such as authentication, electronic voting, and secure multiparty computation ensure desirable security properties if agents follow their prescribed programs. However, if some agents deviate from their prescribed programs and a ...
- ArticleJanuary 2015
Audit games with multiple defender resources
Modern organizations (e.g., hospitals, social networks, government agencies) rely heavily on audit to detect and punish insiders who inappropriately access and disclose confidential information. Recent work on audit games models the strategic ...
- tutorialNovember 2014
WPES 2014: 13th Workshop on Privacy in the Electronic Society
CCS '14: Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications SecurityPages 1546–1547https://doi.org/10.1145/2660267.2660383The 13th Workshop on Privacy in the Electronic Society is held on November 3, 2014 in Scottsdale, Arizona, USA in conjunction with the 21st ACM Conference on Computer and Communications Security. The goal of this workshop is to discuss the problems of ...
- proceedingNovember 2014
WPES '14: Proceedings of the 13th Workshop on Privacy in the Electronic Society
This volume contains the papers selected for presentation at the 13th Workshop on Privacy in the Electronic Society (WPES 2014), held in Scottsdale, Arizona, USA, on November 3, 2014, in conjunction with the ACM Conference on Computer and Communications ...