Pith. sign in

REVIEW 1 cited by

Data Poisoning against Differentially-Private Learners: Attacks and Defenses

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 1903.09860 v2 pith:WE5776AO submitted 2019-03-23 cs.LG cs.CR

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

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners are resistant to data poisoning attacks when the adversary is only able to poison a small number of items. However, this protection degrades as the adversary poisons more data. To illustrate, we design attack algorithms targeting objective and output perturbation learners, two standard approaches to differentially-private machine learning. Experiments show that our methods are effective when the attacker is allowed to poison sufficiently many training items.

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. Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A DP-based certified defense provides lower bounds on expected cumulative reward and per-state action stability for offline RL under transition- and trajectory-level poisoning, with larger certified radii than COPA.

Pith tools