More Like this

1. Types and Abstract Interpretation for Authorization Hook Advice

   Christian Skalka, David Darais (June 2020, Proceedings of the 2020 IEEE Computer Security Foundations Symposium (CSF))

   Authorization hooks are access control checks that prevent unauthorized principals from interacting with some protected resource, and are used extensively in critical software such as operating systems, middleware, and server programs. They are often intended to mediate information flow between subjects (e.g., file owners), but typically in an ad-hoc manner. In this paper we present a static type and effect system for detecting whether authorization hooks in programs properly defend against undesired information flow between subjects. A significant novelty of our approach is an integrated abstract interpretation-based tool that guides system clients through the information flow consequences of access control policy decisions. 

   more » « less
2. Types and Abstract Interpretation for Authorization Hook Advice

   https://doi.org/10.1109/CSF49147.2020.00018  

   Skalka, C.; Darais, D.; Jaeger, T.; Capobianco, F. (June 2021, IEEE Computer Security Foundations Symposium)

   null (Ed.)

   Authorization hooks are access control checks that prevent unauthorized principals from interacting with some protected resource, and are used extensively in critical software such as operating systems, middleware, and server programs. They are often intended to mediate information flow between subjects (e.g., file owners), but typically in an ad-hoc manner. In this paper we present a static type and effect system for detecting whether authorization hooks in programs properly defend against undesired information flow between subjects. A significant novelty of our approach is an integrated abstract interpretation-based tool that guides system clients through the information flow consequences of access control policy decisions. 

   more » « less
3. Differentially Private Empirical Risk Minimization under the Fairness Lens

   Tran, Cuong; Dinh, My; Fioretto, Ferdinando (January 2021, Advances in Neural Information Processing Systems 34 (NeurIPS 2021))

   Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals. This paper builds on these important observations and sheds light on the causes of the disparate impacts arising in the problem of differentially private empirical risk minimization. It focuses on the accuracy disparity arising among groups of individuals in two well-studied DP learning methods: output perturbation and differentially private stochastic gradient descent. The paper analyzes which data and model properties are responsible for the disproportionate impacts, why these aspects are affecting different groups disproportionately, and proposes guidelines to mitigate these effects. The proposed approach is evaluated on several datasets and settings. 

   more » « less
4. On the Fairness Impacts of Private Ensembles Models

   https://doi.org/10.24963/ijcai.2023/57  

   Tran, Cuong; Fioretto, Ferdinando (August 2023, International Joint Conferences on Artificial Intelligence Organization)

   The Private Aggregation of Teacher Ensembles (PATE) is a machine learning framework that enables the creation of private models through the combination of multiple teacher models and a student model. The student model learns to predict an output based on the voting of the teachers, and the resulting model satisfies differential privacy. PATE has been shown to be effective in creating private models in semi-supervised settings or when protecting data labels is a priority.This paper explores whether the use of PATE can result in unfairness, and demonstrates that it can lead to accuracy disparities among groups of individuals. The paper also analyzes the algorithmic and data properties that contribute to these disproportionate impacts, why these aspects are affecting different groups disproportionately, and offers recommendations for mitigating these effects. 

   more » « less
5. Gaps in Information Access in Social Networks

   https://doi.org/10.1145/3308558.3313680  

   Fish, Benjamin; Bashardoust, Ashkan; Boyd, Danah; Friedler, Sorelle; Scheidegger, Carlos; Venkatasubramanian, Suresh (January 2019, The Web Conference (WWW))

   The study of influence maximization in social networks has largely ignored disparate effects these algorithms might have on the individuals contained in the social network. Individuals may place a high value on receiving information, e.g. job openings or advertisements for loans. While well-connected individuals at the center of the network are likely to receive the information that is being distributed through the network, poorly connected individuals are systematically less likely to receive the information, producing a gap in access to the information between individuals. In this work, we study how best to spread information in a social network while minimizing this access gap. We propose to use the maximin social welfare function as an objective function, where we maximize the minimum probability of receiving the information under an intervention. We prove that in this setting this welfare function constrains the access gap whereas maximizing the expected number of nodes reached does not. We also investigate the difficulties of using the maximin, and present hardness results and analysis for standard greedy strategies. Finally, we investigate practical ways of optimizing for the maximin, and give empirical evidence that a simple greedy-based strategy works well in practice. 

   more » « less