Results 741 - 750 of 24392
Alexander Zlokapa is currently a PhD student at MIT co-advised by Isaac Chuang and Aram Harrow, and his research interests include average-case quantum complexity, spin glass theory, Gibbs sampling, and quantum algorithms.
Today, data sharing is the cornerstone of many modern applications. A common concern in such data-sharing pipelines is privacy: organizations are responsible for protecting the privacy of their data, whether it represents user data or enterprise trade secrets. In her talk from the recent workshop on Trust in Decentralized Systems, Giulia Fanti (Carnegie Mellon) discussed emerging challenges related to learning from private, federated data.
Brendan McMahan (Google) presents a framework of principles that helps bring precision to discussions of privacy and AI, and examines the theory and practice required to apply them in real scenarios.
Greetings from Berkeley, where last week we had a doubleheader of workshops associated with our quantum and machine learning pods.
The Simons Institute’s 2022 short documentary, Until the Sun Engulfs the Earth: Lower Bounds in Computational Complexity, is being featured this month in Labocine’s April 2026 issue, mathēmatiká. The documentary asks how we know that a problem is impossible to solve.
Speaker: Rashida Hakim (Columbia University)
Title: Fair Data-Exchange Mechanisms
Abstract: We study data exchange among strategic agents without monetary transfers, motivated by domains such as research consortia and healthcare collaborations where payments are infeasible or restricted. The central challenge is to reap the benefits of data-sharing while preventing free-riding that would otherwise lead agents to under invest in data collection. We introduce a simple fair-exchange contract in which, for every pair of agents, each agent receives exactly as many data points as it provides, equal to the minimum of their two collection levels. We show that the game induced by this contract is supermodular under a transformation of the strategy space. This results in a clean structure: pure Nash equilibria exist, they form a lattice, and can be computed in time quadratic in the number of agents. In addition, the maximal equilibrium is truthfully implementable under natural enforcement assumptions and is globally Pareto-optimal across all strategy profiles. In a graph-restricted variant of the model supermodularity fails, but an adaptation of the construction still yields efficiently computable pure Nash equilibria and Pareto-optimal outcomes. Overall, fair exchange provides a tractable and incentive-aligned mechanism for data exchange in the absence of payments.
Speaker: Chhavi Yadav (CMU, UC Berkeley)
Title: ExpProof : Operationalizing Explanations for Confidential Models with ZKPs , FairProof : Confidential and Certifiable Fairness for Neural Networks
Abstract: In principle, explanations are intended as a way to increase trust in machine learning models and are often obligated by regulations. However, many circumstances where these are demanded are adversarial in nature, meaning the involved parties have misaligned interests and are incentivized to manipulate explanations for their purpose. As a result, explainability methods fail to be operational in such settings despite the demand (Bordt et al., 2022). In this paper, we take a step towards operationalizing explanations in adversarial scenarios with Zero-Knowledge Proofs (ZKPs), a cryptographic primitive. Specifically we explore ZKP-amenable versions of the popular explainability algorithm LIME and evaluate their performance on Neural Networks and Random Forests.
Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose Fairproof -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which is befitting to ZKPs and is used in this system. We implement Fairproof in Gnark and demonstrate empirically that our system is practically feasible.
Modern data marketplaces and data sharing consortia increasingly rely on incentive mechanisms to encourage agents to contribute data. However, schemes that reward agents based solely on the quantity of submitted data are vulnerable to manipulation, as agents may submit fabricated or low-quality data to inflate their rewards. Existing approaches for incentivizing truthful data contributions typically rely on strong assumptions about the underlying data distribution or restrictive models of strategic behavior, limiting their practical applicability.
In this talk, I will present our recent work addressing these challenges. I will begin with our approach to incentivizing truthful data contributions in normal mean estimation problems. I will then describe a more general reward mechanism built on a novel two-sample test inspired by the Cramér–von Mises statistic. We show that truthful reporting constitutes a Nash equilibrium under our framework. I will also briefly highlight some empirical results on real-world language and image datasets demonstrating that our methods effectively promote truthful data sharing.
Relevant papers:
- Chen et al 2023: Mechanism Design for Collaborative Normal Mean Estimation
- Clinton et al 2025, Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
- Clinton et al 2025, A Cramér-von Mises Approach to Incentivizing Truthful Data Sharing