Learning under $p$-Tampering Attacks
Citations
260 citations
160 citations
156 citations
Cites background from "Learning under $p$-Tampering Attack..."
...Attacks restricted to only using correctly label poisoned samples have been explored in prior work, being referred to as “defensible” (Mahloujifar & Mahmoody, 2017; Mahloujifar et al., 2017), “plausible” (Mahloujifar et al....
[...]
...…to only using correctly label poisoned samples have been explored in prior work, being referred to as “defensible” (Mahloujifar & Mahmoody, 2017; Mahloujifar et al., 2017), “plausible” (Mahloujifar et al., 2018; Mahloujifar & Mahmoody, 2018), “visually indistinguishable” (Koh & Liang, 2017),…...
[...]
5 citations
5 citations
References
9,561 citations
8,655 citations
7,994 citations
"Learning under $p$-Tampering Attack..." refers background in this paper
...Such resulting misclassified perturbed instances are called adversarial examples and attacks aimed at finding such examples are called evasion attacks [8,13,22,28,30,44]....
[...]
5,311 citations
"Learning under $p$-Tampering Attack..." refers background or methods in this paper
...In his seminal work [39], Valiant introduced the Probably Approximately Correct (PAC) model of learning that triggered a significant amount of work in the the-...
[...]
...For example, properly learning monomials [39], or using 3-CNF formulae to learn 3-term DNF formulae [31]; the latter Definition 11 (Efficient Realizability)....
[...]
4,505 citations