Poisons that are learned faster are more effective. (arXiv:2204.08615v1 [cs.LG])

Imperceptible poisoning attacks on entire datasets have recently been touted
as methods for protecting data privacy. However, among a number of defenses
preventing the practical use of these techniques, early-stopping stands out as
a simple, yet effective defense. To gauge poisons' vulnerability to
early-stopping, we benchmark error-minimizing, error-maximizing, and synthetic
poisons in terms of peak test accuracy over 100 epochs and make a number of
surprising observations. First, we find that poisons that reach a low training
loss faster have …

lg