Year: 2024
Type: article
Abstract: Perceptual hashing, crucial for detecting and removing image-based sexual abuse (IBSA) online, faces vulnerabilities from low-budget inversion attacks based on generative artificial intelligence. We advocate implementing secure hash matching in IBSA removal tools to mitigate potentially fatal consequences.
Source: IEEE Security & Privacy
Authors: Sophie Hawkes, Christian Weinert, Teresa Almeida, Maryam Mehrnezhad
Institutions: Royal Holloway University of London, Umeå University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G7904777936
OpenAlex ID: W4404576825