all AI news
A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers. (arXiv:2105.13530v2 [cs.LG] UPDATED)
May 13, 2022, 1:11 a.m. | Xi Li, David J. Miller, Zhen Xiang, George Kesidis
cs.LG updates on arXiv.org arxiv.org
Data Poisoning (DP) is an effective attack that causes trained classifiers to
misclassify their inputs. DP attacks significantly degrade a classifier's
accuracy by covertly injecting attack samples into the training set. Broadly
applicable to different classifier structures, without strong assumptions about
the attacker, an {\it unsupervised} Bayesian Information Criterion (BIC)-based
mixture model defense against "error generic" DP attacks is herein proposed
that: 1) addresses the most challenging {\it embedded} DP scenario wherein, if
DP is present, the poisoned samples are …
More from arxiv.org / cs.LG updates on arXiv.org
Digital Over-the-Air Federated Learning in Multi-Antenna Systems
2 days, 11 hours ago |
arxiv.org
Bagging Provides Assumption-free Stability
2 days, 11 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Research Scientist, Demography and Survey Science, University Grad
@ Meta | Menlo Park, CA | New York City
Computer Vision Engineer, XR
@ Meta | Burlingame, CA