Adversarial Privacy Attacks
Adversarial Privacy Attacks is a category of security threats in federated learning wherein malicious entities exploit model updates or system vulnerabilities to infer sensitive private information about individual participants, distinguished from other privacy risks by their deliberate, targeted nature and reliance on adversarial strategies to compromise data confidentiality.
102
Publications
8.1K
Citations
372
Authors
160
Institutions
Publications per year
2017–2026
94
Parents
102
Privacy and Security Issues in Deep Learning: A Survey
Ximeng Liu, Lehui Xie, Jian Zou et al. · IEEE Access · 2020 · 276 citations · Full text
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramèr, Eric Wallace et al. · arXiv (Cornell University) · 2020 · 275 citations · Full text
1–5 of 102
372
5
h-index
4
h-index
4
h-index
3
h-index
3
h-index
1–5 of 372
160
University of California, Berkeley
Berkeley, United States
8 h-index
22 publications
1.4K citations
Berkeley College
New York, United States
6 h-index
19 publications
1.4K citations

University of Electronic Science and Technology of China
Chengdu, China
4 h-index
10 publications
1.3K citations
Google (United States)
Mountain View, United States
4 h-index
10 publications
1.2K citations

Xidian University
Xi'an, China
4 h-index
11 publications
317 citations
Nanyang Technological University
Singapore, Singapore
3 h-index
3 publications
625 citations
Universidad del Noreste
Tampico, Mexico
3 h-index
14 publications
730 citations

Zhejiang University
Hangzhou, China
3 h-index
6 publications
151 citations
1–8 of 160
Repository · 18 publications · 899 citations
13
h-index
3 publications · 134 citations
3
h-index
TKDE · 3 publications · 171 citations
3
h-index
2 publications · 318 citations
2
h-index
2 publications · 406 citations
2
h-index
1–5