Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Florian Tramèr"'
Publikováno v:
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e36be5f5fda3ca15863228f32cf8c506
https://doi.org/10.1145/3548606.3563683
https://doi.org/10.1145/3548606.3563683
Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present in their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c1c75eb3f5b8453d38ffce426658e40
Publikováno v:
David Lindner
Stable Diffusion is a recent open-source image generation model comparable to proprietary models such as DALLE, Imagen, or Parti. Stable Diffusion comes with a safety filter that aims to prevent generating explicit images. Unfortunately, the filter i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1bf663e2911ff111205246ed6c0be74
Publikováno v:
IEEE Security & Privacy. 17:53-61
The Hydra Framework is a new, principled approach to modeling and detecting security-critical bugs. Fusing a variant of classical N-version (redundant) programming with automated bug bounty payouts, Hydra provides economically rigorous and cost-effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56a46442fce6d711ed51135509ac285c
https://doi.org/10.1109/msec.2019.2914109
https://doi.org/10.1109/msec.2019.2914109
Autor:
Mohammad Mahmoody, Samuel Deng, Florian Tramèr, Abhradeep Thakurta, Nicholas Carlini, Sanjam Garg, Somesh Jha, Saeed Mahloujifar
Publikováno v:
IEEE Symposium on Security and Privacy
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algorithm can be made private by relying on an instance-encoding mechanism t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40df1e82a6f4bdf56486e6148babfa01
https://doi.org/10.1109/sp40001.2021.00099
https://doi.org/10.1109/sp40001.2021.00099
Autor:
Lie He, Sebastian U. Stich, Mariana Raykova, Phillip B. Gibbons, Mehryar Mohri, David Evans, Badih Ghazi, Felix X. Yu, Sen Zhao, Jianyu Wang, Zheng Xu, Weikang Song, Prateek Mittal, Ramesh Raskar, Zachary Garrett, Farinaz Koushanfar, H. Brendan McMahan, Ayfer Ozgur, Mikhail Khodak, Rafael G. L. D'Oliveira, Jakub Konecní, Aurélien Bellet, Arjun Nitin Bhagoji, Hubert Eichner, Han Yu, Adrià Gascón, Ananda Theertha Suresh, Sanmi Koyejo, Praneeth Vepakomma, Josh Gardner, Chaoyang He, Florian Tramèr, Tancrède Lepoint, Salim El Rouayheb, Peter Kairouz, Li Xiong, Kallista Bonawitz, Rasmus Pagh, Tara Javidi, Mehdi Bennis, Dawn Song, Martin Jaggi, Zhouyuan Huo, Hang Qi, Gauri Joshi, Qiang Yang, Richard Nock, Yang Liu, Brendan Avent, Justin Hsu, Rachel Cummings, Graham Cormode, Marco Gruteser, Aleksandra Korolova, Ziteng Sun, Zaid Harchaoui, Ben Hutchinson, Zachary Charles, Daniel Ramage
Publikováno v:
Foundations and Trends in Machine Learning
Foundations and Trends in Machine Learning, 2021, 14 (1-2), pp.1-210
Foundations and Trends in Machine Learning, Now Publishers, 2021, 14 (1-2), pp.1-210
Foundations and Trends in Machine Learning, 2021, 14 (1-2), pp.1-210
Foundations and Trends in Machine Learning, Now Publishers, 2021, 14 (1-2), pp.1-210
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b1ccc10027ba1ce68ce0210510e8bdc
https://inria.hal.science/hal-02406503v2/document
https://inria.hal.science/hal-02406503v2/document
Autor:
Florian Tramèr, Varun Chandrasekaran, Homa Alemzadeh, Karthik Pattabiraman, Nicolas Papernot, Guanpeng Li, Rakesh B. Bobba, Hui Xu, David Evans
Publikováno v:
DSN Workshops
On behalf of the Organizing Committee, it is our pleasure to welcome you to the fourth International Workshop on Dependable and Secure Machine Learning (DSML). This year, due to the COVID-19 situation, the DSML workshop will be held online, in conjun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::98f910ea339a5fa36fb180e34983204f
https://doi.org/10.1109/dsn-w50199.2020.00006
https://doi.org/10.1109/dsn-w50199.2020.00006
Publikováno v:
NDSS
Incentive mechanisms are central to the functionality of permissionless blockchains: they incentivize participants to run and secure the underlying consensus protocol. Designing incentive-compatible incentive mechanisms is notoriously challenging, ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3f133d19c4a80450698752e4d0d27d3
http://arxiv.org/abs/1912.01798
http://arxiv.org/abs/1912.01798
Autor:
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawit, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D’Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
The term Federated Learning was coined as recently as 2016 to describe a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client's
Publikováno v:
CCS
Perceptual ad-blocking is a novel approach that detects online advertisements based on their visual content. Compared to traditional filter lists, the use of perceptual signals is believed to be less prone to an arms race with web publishers and ad n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a06ba9d14bc1ebf25cb5c2dd58ceae8
https://doi.org/10.1145/3319535.3354222
https://doi.org/10.1145/3319535.3354222