2 papers
cs.LG2022
Robustly-reliable learners under poisoning attacks
Maria-Florina Balcan, Avrim Blum, Steve Hanneke +1
Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibilit…
cs.LG2021
Robust learning under clean-label attack
Avrim Blum, Steve Hanneke, Jian Qian +1
We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to…