The paper proposes a RowHammer-based DRAM true random number generator, EIM-TRNG, and claims it can obfuscate DNN weights, but the key randomness and the weight-obfuscation evidence are not validated.
Secureml: A system for scalable privacy- preserving machine learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
The paper proposes a RowHammer-based DRAM true random number generator, EIM-TRNG, and claims it can obfuscate DNN weights, but the key randomness and the weight-obfuscation evidence are not validated.