Joseph Lorenzo Hall, PhD on Nostr: Think your proprietary AI is safe behind closed doors? Xiao et al. introduce ...

Think your proprietary AI is safe behind closed doors? Xiao et al. introduce ModelSpy, a side-channel attack that steals complete neural network architectures from up to six meters away just by listening to a GPU's electromagnetic leakage through a wall. https://www.ndss-symposium.org/ndss-paper/peering-inside-the-black-box-long-range-and-scalable-model-architecture-snooping-via-gpu-electromagnetic-side-channel/