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.
Prediction poisoning: Towards defenses against dnn model stealing attacks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
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.
-
Lossless Anti-Distillation Sampling
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.