no code implementations • 12 Mar 2024 • Zachary McBride Lazri, Danial Dervovic, Antigoni Polychroniadou, Ivan Brugere, Dana Dachman-Soled, Min Wu
Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier.
no code implementations • 6 Feb 2024 • Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled, Danial Dervovic, Antigoni Polychroniadou, Min Wu
The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset.
no code implementations • 23 Oct 2023 • Zachary McBride Lazri, Ivan Brugere, Xin Tian, Dana Dachman-Soled, Antigoni Polychroniadou, Danial Dervovic, Min Wu
The mapping is constructed to preserve the relative relationship between the scores obtained from the unprocessed feature vectors of individuals from the same demographic group, guaranteeing within-group fairness.
no code implementations • 9 Jul 2020 • Mingliang Chen, Aria Shahverdi, Sarah Anderson, Se Yong Park, Justin Zhang, Dana Dachman-Soled, Kristin Lauter, Min Wu
The three tools are: - A new definition of fairness called "controlled fairness" with respect to choices of protected features and filters.
1 code implementation • ICLR 2020 • Sanghyun Hong, Michael Davinroy, Yiǧitcan Kaya, Dana Dachman-Soled, Tudor Dumitraş
New data processing pipelines and novel network architectures increasingly drive the success of deep learning.
1 code implementation • 17 Feb 2020 • Sanghyun Hong, Michael Davinroy, Yiğitcan Kaya, Dana Dachman-Soled, Tudor Dumitraş
This provides an incentive for adversaries to steal these novel architectures; when used in the cloud, to provide Machine Learning as a Service, the adversaries also have an opportunity to reconstruct the architectures by exploiting a range of hardware side channels.
1 code implementation • ICLR 2019 • Sanghyun Hong, Michael Davinroy, Yiǧitcan Kaya, Stuart Nevans Locke, Ian Rackow, Kevin Kulda, Dana Dachman-Soled, Tudor Dumitraş
Based on the extracted architecture attributes, we also demonstrate that an attacker can build a meta-model that accurately fingerprints the architecture and family of the pre-trained model in a transfer learning setting.
no code implementations • 21 May 2014 • Dana Dachman-Soled, Vitaly Feldman, Li-Yang Tan, Andrew Wan, Karl Wimmer
We study the notion of $\mathit{approximate}$ $\mathit{resilience}$ of Boolean functions, where we say that $f$ is $\alpha$-approximately $d$-resilient if $f$ is $\alpha$-close to a $[-1, 1]$-valued $d$-resilient function in $\ell_1$ distance.