Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Shruti Tople"'
Publikováno v:
ICDCS
Peer-to-peer (P2P) systems such as BitTorrent and Bitcoin are susceptible to serious attacks from byzantine nodes that join as peers. Due to well-known impossibility results for designing P2P primitives in unrestricted byzantine settings, research ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e189a38e1d4f2858942b6a5dd1c98172
https://doi.org/10.1109/icdcs47774.2020.00134
https://doi.org/10.1109/icdcs47774.2020.00134
Autor:
Marc Brockschmidt, Santiago Zanella-Béguelin, Andrew Paverd, Lukas Wutschitz, Victor Rühle, Olga Ohrimenko, Boris Köpf, Shruti Tople
Publikováno v:
CCS
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update can reveal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43b8e2503af3226e4dd6122e3dfc2b92
https://doi.org/10.1145/3372297.3417880
https://doi.org/10.1145/3372297.3417880
Publikováno v:
Proceedings on Privacy Enhancing Technologies, Vol 2021, Iss 1, Pp 188-208 (2021)
We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such as VGG16
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fd2f906345c0734e57adc4227762935
Publikováno v:
Applied Cryptography and Network Security ISBN: 9783319933863
ACNS
ACNS
In cloud computing, where clients are billed based on the consumed resources for outsourced tasks, both the cloud providers and the clients have the incentive to manipulate claims about resource usage. Both desire an accurate and verifiable resource
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ab1bc906275b2c5e4e8cc4fdc3925d5
https://doi.org/10.1007/978-3-319-93387-0_34
https://doi.org/10.1007/978-3-319-93387-0_34
Publikováno v:
Computer Security – ESORICS 2017 ISBN: 9783319663982
ESORICS (2)
ESORICS (2)
Privacy and anonymity are important desiderata in the use of cryptocurrencies. Monero—a privacy centric cryptocurrency has rapidly gained popularity due to its unlinkability and untraceablity guarantees. It has a market capitalization of USD 290M.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef97bad242a74866b76d965d17259af9
https://doi.org/10.1007/978-3-319-66399-9_9
https://doi.org/10.1007/978-3-319-66399-9_9
Autor:
Prateek Saxena, Shruti Tople
Publikováno v:
Detection of Intrusions and Malware, and Vulnerability Assessment ISBN: 9783319608754
DIMVA
DIMVA
To enable privacy-preserving computation on encrypted data, a class of techniques for input-oblivious execution have surfaced. The property of input-oblivious execution guarantees that an adversary observing the interaction of a program with the unde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cde463128b52d9de3eb7aa1bb9c1a96
https://doi.org/10.1007/978-3-319-60876-1_2
https://doi.org/10.1007/978-3-319-60876-1_2
Publikováno v:
NDSS
Intel SGX, a new security capability in emerging CPUs, allows user-level application code to execute in hardware isolated enclaves. Enclave memory is isolated from all other software on the system, even from the privileged OS or hypervisor. While bei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70f468e1e7d36ec40ec3ee5e8c16e524
https://doi.org/10.14722/ndss.2017.23500
https://doi.org/10.14722/ndss.2017.23500
Publikováno v:
ACSAC
Deep learning in a collaborative setting is emerging as a corner-stone of many upcoming applications, wherein untrusted users collaborate to generate more accurate models. From the security perspective, this opens collaborative deep learning to poiso
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7bb5caacd7b667c018eb06376afe4402
https://doi.org/10.1145/2991079.2991125
https://doi.org/10.1145/2991079.2991125
Publikováno v:
ACM Conference on Computer and Communications Security
Web servers are vulnerable to a large class of attacks which can allow network attacker to steal sensitive web content. In this work, we investigate the feasibility of a web server architecture, wherein the vulnerable server VM runs on a trusted clou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ebadd6e494dacf248311f2fc8cc3d8e
https://doi.org/10.1145/2508859.2516666
https://doi.org/10.1145/2508859.2516666
Publikováno v:
ACM Conference on Computer and Communications Security
Web browsers isolate web origins, but do not provide direct abstractions to isolate sensitive data and control computation over it within the same origin. As a result, guaranteeing security of sensitive web content requires trusting all code in the b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f5cf73930324bbb7ee72b6b36c1ce619
https://doi.org/10.1145/2508859.2516743
https://doi.org/10.1145/2508859.2516743