The paper gives closed-form optimal data-poisoning attacks on PCA, showing the worst-case subspace rotation depends only on the k-th and (k+1)-th singular values and the attacker's energy budget.
Adversarial principal component analysis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Adversarial Robustness of Subspace Learning
The paper gives closed-form optimal data-poisoning attacks on PCA, showing the worst-case subspace rotation depends only on the k-th and (k+1)-th singular values and the attacker's energy budget.