Zobrazeno 1 - 10
of 194
pro vyhledávání: '"Somesh, Jha"'
Publikováno v:
ACM Transactions on Cyber-Physical Systems. 7:1-6
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::572110792e247abfeb5580fa3acc8da5
https://doi.org/10.1145/3579986
https://doi.org/10.1145/3579986
Publikováno v:
Proceedings of the ACM on Programming Languages. 6:1-29
To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation , primarily using the interval abstract domain. In this paper, we study the theoretical power and limits of the interval domain for neur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f42d60e363005b2d3af9583d16d094b
https://doi.org/10.1145/3498675
https://doi.org/10.1145/3498675
Publikováno v:
Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security.
There is great demand for scalable, secure, and efficient privacy-preserving machine learning models that can be trained over distributed data. While deep learning models typically achieve the best results in a centralized non-secure setting, differe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23abf4eeda9a4a91aa49b724196fa914
https://doi.org/10.1145/3548606.3560687
https://doi.org/10.1145/3548606.3560687
Autor:
Jignesh M. Patel, Gabriela Ciocarlie, Dongyan Xu, Xiangyu Zhang, Ashish Gehani, Somesh Jha, Hassaan Irshad, Kyu Hyung Lee, Vinod Yegneswaran, Yonghwi Kwon
Publikováno v:
IEEE Transactions on Information Forensics and Security. 16:4363-4376
We present TRACE, a comprehensive provenance tracking system for scalable, real-time, enterprise-wide APT detection. TRACE uses static analysis to identify program unit structures and inter-unit dependences, such that the provenance of an output even
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc6a420d12f95877d15e6b2dce42701c
https://doi.org/10.1109/tifs.2021.3098977
https://doi.org/10.1109/tifs.2021.3098977
Autor:
Ujjaini Dasgupta, Raunak Kar, Devashish Mehta, Vijay Soni, Pankaj Sharma, Somesh Jha, Aasheesh Srivastava, Sanjay Pal, Poonam Yadav, Vinay Kumar Nandicoori, Kajal Rana, D Jain, Veena S. Patil, Avinash Bajaj, Nihal Medatwal, Sandeep Kumar
Publikováno v:
Nanoscale. 13:13225-13230
We present a non-immunogenic, injectable, low molecular weight, amphiphilic hydrogel-based drug delivery system (TB-Gel) that can entrap a cocktail of four front-line antitubercular drugs, isoniazid, rifampicin, pyrazinamide, and ethambutol. We showe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdc72bc6ce97cdd62bed0a617c065815
https://doi.org/10.1039/d0nr08806d
https://doi.org/10.1039/d0nr08806d
Autor:
Bolin Ding, Cheng Hong, Ninghui Li, Min Xu, Tianhao Wang, Zhicong Huang, Somesh Jha, Jingren Zhou
Publikováno v:
Proceedings of the VLDB Endowment. 13:3545-3558
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each user executes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bde0a5929c17003389c45a5ea26d927c
https://doi.org/10.14778/3424573.3424576
https://doi.org/10.14778/3424573.3424576
Publikováno v:
Journal of Computer Security. 28:35-70
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e0cecda31ae5f08847da6c4d6e06ad5
https://doi.org/10.3233/jcs-191362
https://doi.org/10.3233/jcs-191362
Federated learning (FL) enables clients to collaborate with a server to train a machine learning model. To ensure privacy, the server performs secure aggregation of updates from the clients. Unfortunately, this prevents verification of the well-forme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e326bc1413df21c29e078f727ee41ae
http://arxiv.org/abs/2112.12727
http://arxiv.org/abs/2112.12727
Autor:
Joann Qiongna Chen, Somesh Jha, Ninghui Li, Tianhao Wang, Dong Su, Zhou Li, Zhikun Zhang, Yueqiang Cheng
Publikováno v:
CCS
In this paper, we study the problem of publishing a stream of real-valued data satisfying differential privacy (DP). One major challenge is that the maximal possible value can be quite large; thus it is necessary to estimate a threshold so that numbe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0475d1543e48f51b3f5cb551b6d25b22
https://doi.org/10.1145/3460120.3484750
https://doi.org/10.1145/3460120.3484750
Autor:
Avinash Bajaj, Sarita Mishra, Devashish Mehta, Munia Ganguli, Kajal Rana, Sandeep Kumar, Aasheesh Srivastava, Kajal Rajput, Somesh Jha, Manas Kumar Pradhan, Jyoti Thakur, Sanjay Pal, Veena S. Patil, Ujjaini Dasgupta, D Jain, Parul Rani, Animesh Kar, Raunak Kar
Publikováno v:
ACS applied materialsinterfaces. 13(37)
Treatment of chronic wound infections caused by Gram-positive bacteria such as Staphylococcus aureus is highly challenging due to the low efficacy of existing formulations, thereby leading to drug resistance. Herein, we present the synthesis of a non
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00fd37f436f0513633981d45adfaaa6c
https://pubmed.ncbi.nlm.nih.gov/34491724
https://pubmed.ncbi.nlm.nih.gov/34491724