no code implementations • 19 Feb 2024 • Theresa Stadler, Bogdan Kulynych, Nicoals Papernot, Michael Gastpar, Carmela Troncoso
The promise of least-privilege learning -- to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this task -- is highly appealing.
no code implementations • 24 Aug 2023 • Avni Kothari, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun
In turn, models can assign predictions that are fixed, meaning that consumers who are denied loans, interviews, or benefits may be permanently locked out from access to credit, employment, or assistance.
1 code implementation • 28 Feb 2023 • Bogdan Kulynych, Hsiang Hsu, Carmela Troncoso, Flavio P. Calmon
We demonstrate that such randomization incurs predictive multiplicity: for a given input example, the output predicted by equally-private models depends on the randomness used in training.
no code implementations • 27 Aug 2022 • Klim Kireev, Bogdan Kulynych, Carmela Troncoso
We argue that, due to the differences between tabular data and images or text, existing threat models are not suitable for tabular domains.
1 code implementation • 7 Apr 2022 • Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jarosław Błasiok, Preetum Nakkiran
In contrast, we show that Differentially-Private (DP) training provably ensures the high-level WYSIWYG property, which we quantify using a notion of distributional generalization.
no code implementations • ICML Workshop AML 2021 • Kendra Albert, Maggie Delano, Bogdan Kulynych, Ram Shankar Siva Kumar
In this paper, we review the broader impact statements that adversarial ML researchers wrote as part of their NeurIPS 2020 papers and assess the assumptions that authors have about the goals of their work.
no code implementations • 5 Jul 2021 • Agathe Balayn, Bogdan Kulynych, Seda Guerses
Researchers have identified datasets used for training computer vision (CV) models as an important source of hazardous outcomes, and continue to examine popular CV datasets to expose their harms.
2 code implementations • 2 Jun 2019 • Bogdan Kulynych, Mohammad Yaghini, Giovanni Cherubin, Michael Veale, Carmela Troncoso
Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model.
no code implementations • 27 Nov 2018 • Rebekah Overdorf, Bogdan Kulynych, Ero Balsa, Carmela Troncoso, Seda Gürses
In addition to their benefits, optimization systems can have negative economic, moral, social, and political effects on populations as well as their environments.
2 code implementations • 25 Oct 2018 • Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso
We introduce a graphical framework that (1) generalizes existing attacks in discrete domains, (2) can accommodate complex cost functions beyond $p$-norms, including financial cost incurred when attacking a classifier, and (3) efficiently produces valid adversarial examples with guarantees of minimal adversarial cost.
1 code implementation • 7 Jun 2018 • Bogdan Kulynych, Rebekah Overdorf, Carmela Troncoso, Seda Gürses
Fairness frameworks do so, in part, by mapping these problems to a narrow definition and assuming the service providers can be trusted to deploy countermeasures.
no code implementations • 14 Nov 2017 • Bogdan Kulynych, Carmela Troncoso
In particular, we propose the use of the Banzhaf power index as a measure of influence of features on the outcome of a classifier.
2 code implementations • 19 Jul 2017 • Bogdan Kulynych, Wouter Lueks, Marios Isaakidis, George Danezis, Carmela Troncoso
Autocrypt is a new community-driven open specification for e-mail encryption that attempts to respond to this demand.
Cryptography and Security