Pith. sign in

REVIEW 1 cited by

Learning and Certification under Instance-targeted Poisoning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.08709 v2 pith:CVJ5RAHM submitted 2021-05-18 cs.LG cs.CR

classification cs.LGcs.CR
keywords adversarylearningattackscertificationinstance-targetedpoisoningunderattack
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the learner at the test instance. Our first contribution is to formalize the problem in various settings and to explicitly model subtle aspects such as the proper or improper nature of the learning, learner's randomness, and whether (or not) adversary's attack can depend on it. Our main result shows that when the budget of the adversary scales sublinearly with the sample complexity, (improper) PAC learnability and certification are achievable; in contrast, when the adversary's budget grows linearly with the sample complexity, the adversary can potentially drive up the expected 0-1 loss to one. We also study distribution-specific PAC learning in the same attack model and show that proper learning with certification is possible for learning half spaces under natural distributions. Finally, we empirically study the robustness of K nearest neighbour, logistic regression, multi-layer perceptron, and convolutional neural network on real data sets against targeted-poisoning attacks. Our experimental results show that many models, especially state-of-the-art neural networks, are indeed vulnerable to these strong attacks. Interestingly, we observe that methods with high standard accuracy might be more vulnerable to instance-targeted poisoning attacks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness

    cs.LG 2025-06 conditional novelty 8.0 of 10

    The optimal excess error for agnostic learning under instance-targeted poisoning is eTheta(sqrt(d eta)), achieved by a randomized learner and unavoidable even against adversaries who see the learner's random seed.

Pith tools