Zobrazeno 1 - 10
of 417
pro vyhledávání: '"Vorobeychik, Yevgeniy"'
Autor:
Zhang, Tao, Venkatesaraman, Rajagopal, De, Rajat K., Malin, Bradley A., Vorobeychik, Yevgeniy
An ability to share data, even in aggregated form, is critical to advancing both conventional and data science. However, insofar as such datasets are comprised of individuals, their membership in these datasets is often viewed as sensitive, with memb
Externí odkaz:
http://arxiv.org/abs/2410.07414
Autor:
Liu, Xiaogeng, Li, Peiran, Suh, Edward, Vorobeychik, Yevgeniy, Mao, Zhuoqing, Jha, Somesh, McDaniel, Patrick, Sun, Huan, Li, Bo, Xiao, Chaowei
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), a
Externí odkaz:
http://arxiv.org/abs/2410.05295
We introduce a novel privacy notion of ($\epsilon, \delta$)-confounding privacy that generalizes both differential privacy and Pufferfish privacy. In differential privacy, sensitive information is contained in the dataset while in Pufferfish privacy,
Externí odkaz:
http://arxiv.org/abs/2408.12010
We introduce a policy model coupled with the susceptible-infected-recovered (SIR) epidemic model to study interactions between policy-making and the dynamics of epidemics. We consider both single-region policies, as well as game-theoretic models invo
Externí odkaz:
http://arxiv.org/abs/2408.02097
Autor:
Borza, Victor, Estornell, Andrew, Clayton, Ellen Wright, Ho, Chien-Ju, Rothman, Russell, Vorobeychik, Yevgeniy, Malin, Bradley
Large participatory biomedical studies, studies that recruit individuals to join a dataset, are gaining popularity and investment, especially for analysis by modern AI methods. Because they purposively recruit participants, these studies are uniquely
Externí odkaz:
http://arxiv.org/abs/2408.01375
Our society collects data on people for a wide range of applications, from building a census for policy evaluation to running meaningful clinical trials. To collect data, we typically sample individuals with the goal of accurately representing a popu
Externí odkaz:
http://arxiv.org/abs/2407.00170
This paper focuses on the challenge of machine unlearning, aiming to remove the influence of specific training data on machine learning models. Traditionally, the development of unlearning algorithms runs parallel with that of membership inference at
Externí odkaz:
http://arxiv.org/abs/2406.07687
Autor:
Sarkar, Anindya, Sastry, Srikumar, Pirinen, Aleksis, Zhang, Chongjie, Jacobs, Nathan, Vorobeychik, Yevgeniy
We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. This could emulate a UAV involved in a search-an
Externí odkaz:
http://arxiv.org/abs/2406.01917
Autor:
Zhang, Tao, Venkatesaramani, Rajagopal, De, Rajat K., Malin, Bradley A., Vorobeychik, Yevgeniy
The advent of online genomic data-sharing services has sought to enhance the accessibility of large genomic datasets by allowing queries about genetic variants, such as summary statistics, aiding care providers in distinguishing between spurious geno
Externí odkaz:
http://arxiv.org/abs/2406.01811
Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning verified safe
Externí odkaz:
http://arxiv.org/abs/2405.15994