Lipschitz-style certificates pass for EEGNet and classical BCI decoders while PGD accuracy drops up to 25.7% at ε=0.25, and related fidelity and privacy audits reveal further objective-user welfare mismatches.
Concrete problems in AI safety, 2016
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Certificates Fail: A Unified Safety Framework for Embedded Neural Interface Models
Lipschitz-style certificates pass for EEGNet and classical BCI decoders while PGD accuracy drops up to 25.7% at ε=0.25, and related fidelity and privacy audits reveal further objective-user welfare mismatches.