Floating-point neural networks with automatic differentiation can represent arbitrary floating-point functions and their gradients under mild conditions.
Proceedings of the 22nd ACM SIGSAC conference on computer and communications security , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.
citing papers explorer
-
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
An attack aligns differently shuffled intermediate activations from secure Transformer inference queries to recover model weights with low error using roughly one dollar of queries.