no code implementations • 3 Apr 2024 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Charting the susceptibility of T2I models to such manipulation, we first expose the new possibility of a dynamic and computationally efficient exploitation of model bias by targeting the embedded language models.
no code implementations • 20 Dec 2023 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas.
1 code implementation • 31 Jul 2023 • Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Based on the penetration level, BAGM takes the form of a suite of attacks that are referred to as surface, shallow and deep attacks in this article.