Andi Zhang
@az381.bsky.social
📤 0
📥 2
📝 1
Assistant Professor @ The University of Warwick
Many thanks to the UKRI AI Hub in Generative Models for featuring our work and for their support of this research.
add a skeleton here at some point
about 1 month ago
0
2
1
reposted by
Andi Zhang
Gen AI - the AI Hub in Generative Models
about 1 month ago
A method for testing AI safety by using human-like concepts to trick generative models into making mistakes, has been developed by Hub researchers. The paper, entitled Concept-based Adversarial Attack: A Probabilistic Perspective, is summarised on our website:
www.genai.ac.uk/news/hub-res...
0
1
2
you reached the end!!
feeds!
log in