Alexander Levine, Soheil Feizi, Wenxiao Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an aggregation of base classifiers trained on disjoint subsets of data, thus restricting its sensitivity to dataset distortions. In this work, we propose an improved certified defense against general poisoning attacks, namely Finite Aggregation. In contrast to DPA, which directly splits the training set into disjoint subsets, our method first splits the training set into smaller disjoint subsets and then combines duplicates of them to build larger (but not disjoint) subsets for training base classifiers. This reduces the worst-case impacts of poison samples and thus improves certified robustness bounds. In addition, we offer an alternative view of our method, bridging the designs of deterministic and stochastic aggregation-based certified defenses. Empirically, our proposed Finite Aggregation consistently improves certificates on MNIST, CIFAR-10, and GTSRB, boosting certified fractions by up to 3.05%, 3.87% and 4.77%, respectively, while keeping the same clean accuracies as DPA's, effectively establishing a new state of the art in (pointwise) certified robustness against data poisoning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.02628")
get_code_for_paper("2202.02628")
have("2202.02628")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.02628.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.02628)
Connect an agent — have() is free.