all InfoSec news
TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets. (arXiv:2303.05762v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Diffusion models have achieved great success in a range of tasks, such as
image synthesis and molecule design. As such successes hinge on large-scale
training data collected from diverse sources, the trustworthiness of these
collected data is hard to control or audit. In this work, we aim to explore the
vulnerabilities of diffusion models under potential training data manipulations
and try to answer: How hard is it to perform Trojan attacks on well-trained
diffusion models? What are the adversarial targets …
aim attacks audit control data design diffusion models great hard large scale training trojan under vulnerabilities work