LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing
This work shows that one can extract LLM assets during inference, namely embeddings, attention, and quantized MLP weights, activations, and other inference states, from localized memories and compute subcircuits from localized memories and compute subcircuits by deploying laser voltage imaging.
Dev M. Mehta, Lily Dukette, William Folan et al.
· 0 citations