What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning. (arXiv:2102.13624v2 [cs.LG] UPDATED)

Data poisoning is a threat model in which a malicious actor tampers with
training data to manipulate outcomes at inference time. A variety of defenses
against this threat model have been proposed, but each suffers from at least
one of the following flaws: they are easily overcome by adaptive attacks, they
severely reduce testing performance, or they cannot generalize to diverse data
poisoning threat models. Adversarial training, and its variants, are currently
considered the only empirically strong defense against (inference-time) …

data data poisoning kill lg poisoning train