English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The rise in popularity of text-to-image generative artificial intelligence(AI) has attracted widespread public interest. We demonstrate that thistechnology can be attacked to generate content that subtly manipulates itsusers. We propose a Backdoor Attack on text-to-image Generative Models (BAGM),which upon triggering, infuses the generated images with manipulative detailsthat are naturally blended in the content. Our attack is the first to targetthree popular text-to-image generative models across three stages of thegenerative process by modifying the behaviour of the embedded tokenizer, thelanguage model or the image generative model. 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. Given the existing gap within thisdomain, we also contribute a comprehensive set of quantitative metrics designedspecifically for assessing the effectiveness of backdoor attacks ontext-to-image models. The efficacy of BAGM is established by attackingstate-of-the-art generative models, using a marketing scenario as the targetdomain. To that end, we contribute a dataset of branded product images. Ourembedded backdoors increase the bias towards the target outputs by more thanfive times the usual, without compromising the model robustness or thegenerated content utility. By exposing generative AI's vulnerabilities, weencourage researchers to tackle these challenges and practitioners to exercisecaution when using pre-trained models. Relevant code, input prompts andsupplementary material can be found at https://github.com/JJ-Vice/BAGM, and thedataset is available at:https://ieee-dataport.org/documents/marketable-foods-mf-dataset.  Keywords: Generative Artificial Intelligence, Generative Models,Text-to-Image generation, Backdoor Attacks, Trojan, Stable Diffusion.

BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models