2 citations · 2 across the 4 of their papers we have counts for
4 papers · 1 filter
Proofs as Explanations: Short Certificates for Reliable Predictions
Avrim Blum, Steve Hanneke, Chirag Pabbaraju +1
We consider a model for explainable AI in which an explanation for a prediction consists of a subset of the training data (if it exists) such that all classifiers $h'…
Reliable learning in challenging environments
Maria-Florina Balcan, Steve Hanneke, Rattana Pukdee +1
The problem of designing learners that provide guarantees that their predictions are provably correct is of increasing importance in machine learning. However, learning theoretic g…
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…
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…