Establishes that no defense works against linear-proportion poisoning with unbounded noise in regularization-based continual learning and proposes verification and robust defenses for infrequent or bounded attacks.
arXiv preprint arXiv:2207.05225 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Theory of Continual Learning Against Data Poisoning Attacks
Establishes that no defense works against linear-proportion poisoning with unbounded noise in regularization-based continual learning and proposes verification and robust defenses for infrequent or bounded attacks.