Web sites;
Social networking (online);
Privacy;
Image reconstruction;
Databases;
Videos;
Safety;
Robustness;
Fingerprint recognition;
Encryption;
D O I:
10.1109/MSEC.2024.3485497
中图分类号:
TP [自动化技术、计算机技术];
学科分类号:
0812 ;
摘要:
We show that perceptual hashing, crucial for detecting and removing image-based sexual abuse (IBSA) online, faces vulnerabilities from low-budget inversion attacks based on generative AI. This jeopardizes the privacy of users, especially vulnerable groups. We advocate to implement secure hash matching in IBSA removal tools to mitigate potentially fatal consequences.
机构:
RMIT Univ, Social & Global Studies Ctr, Melbourne, Vic, AustraliaRMIT Univ, Social & Global Studies Ctr, Melbourne, Vic, Australia
Henry, Nicola
Flynn, Asher
论文数: 0引用数: 0
h-index: 0
机构:
Monash Univ, Sch Social Sci, Criminol, Clayton, Vic, Australia
Monash Univ, Sch Social Sci, Social & Polit Sci Grad Res Program, Clayton, Vic, AustraliaRMIT Univ, Social & Global Studies Ctr, Melbourne, Vic, Australia
Flynn, Asher
论文数: 引用数:
h-index:
机构:
Powell, Anastasia
TRENDS AND ISSUES IN CRIME AND CRIMINAL JUSTICE,
2019,
(572):
: 1
-
19
机构:
Monash Univ, Sch Social Sci, Criminol, 20 Chancellors Walk, Clayton, Vic 3800, AustraliaMonash Univ, Sch Social Sci, Criminol, 20 Chancellors Walk, Clayton, Vic 3800, Australia
Flynn, Asher
Cama, Elena
论文数: 0引用数: 0
h-index: 0
机构:
Univ New South Wales, Ctr Social Res Hlth, Sydney, NSW, AustraliaMonash Univ, Sch Social Sci, Criminol, 20 Chancellors Walk, Clayton, Vic 3800, Australia
Cama, Elena
论文数: 引用数:
h-index:
机构:
Powell, Anastasia
Scott, Adrian J.
论文数: 0引用数: 0
h-index: 0
机构:
Goldsmiths Univ London, Dept Psychol, London, EnglandMonash Univ, Sch Social Sci, Criminol, 20 Chancellors Walk, Clayton, Vic 3800, Australia