Timezone: »

 
Poster
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Xuanqing Liu · Si Si · Jerry Zhu · Yang Li · Cho-Jui Hsieh

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #24
in Algorithms -- Semi-Supervised Learning »
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals and constraints into a single formula for data poisoning attack in G-SSL, then we propose two specialized algorithms to efficiently solve two important cases --- poisoning regression tasks under $\ell_2$-norm constraint and classification tasks under $\ell_0$-norm constraint. In the former case, we transform it into a non-convex trust region problem and show that our gradient-based algorithm with delicate initialization and update scheme finds the (globally) optimal perturbation. For the latter case, although it is an NP-hard integer programming problem, we propose a probabilistic solver that works much better than the classical greedy method. Lastly, we test our framework on real datasets and evaluate the robustness of G-SSL algorithms. For instance, on the MNIST binary classification problem (50000 training data with 50 labeled), flipping two labeled data is enough to make the model perform like random guess (around 50\% error).
Keywords: Semi-Supervised Learning · Privacy, Anonymity, and Security · Applications · Algorithms
[ Paper]  [ Poster] 

Author Information

Xuanqing Liu (University of California, Los Angeles)
Si Si (Google Research)
Jerry Zhu (University of Wisconsin-Madison)
Yang Li (Google)

Yang Li is a Senior Staff Research Scientist at Google, and an affiliate faculty member at the University of Washington CSE, focusing on the area intersecting AI and HCI. He pioneered on-device interactive ML on Android by developing impactful product features such as next app prediction and Gesture Search. Yang has extensively published in top venues across both the HCI and ML fields, including CHI, UIST, ICML, ACL, EMNLP, CVPR, NeurIPS (NIPS), ICLR, and KDD, and has constantly served as area chairs or senior area (track) chairs across the fields. Yang is also an editor of the upcoming Springer book on "AI for HCI: A Modern Approach", which is the first thorough treatment of the topic.

Cho-Jui Hsieh (UCLA)

More from the Same Authors