all InfoSec news
Decision-based iterative fragile watermarking for model integrity verification. (arXiv:2305.09684v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Typically, foundation models are hosted on cloud servers to meet the high
demand for their services. However, this exposes them to security risks, as
attackers can modify them after uploading to the cloud or transferring from a
local system. To address this issue, we propose an iterative decision-based
fragile watermarking algorithm that transforms normal training samples into
fragile samples that are sensitive to model changes. We then compare the output
of sensitive samples from the original model to that of …
address attackers cloud decision demand foundation foundation models high integrity issue local risks security security risks servers services system verification watermarking