all InfoSec news
Temporal Robustness against Data Poisoning. (arXiv:2302.03684v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Data poisoning considers cases when an adversary maliciously inserts and
removes training data to manipulate the behavior of machine learning
algorithms. Traditional threat models of data poisoning center around a single
metric, the number of poisoned samples. In consequence, existing defenses are
essentially vulnerable in practice when poisoning more samples remains a
feasible option for attackers. To address this issue, we leverage timestamps
denoting the birth dates of data, which are often available but neglected in
the past. Benefiting from …
address adversary algorithms attackers cases center data data poisoning issue machine machine learning machine learning algorithms poisoning practice robustness single temporal threat threat models training vulnerable