Timezone: »

 
Poster
An Efficient Adversarial Attack for Tree Ensembles
Chong Zhang · Huan Zhang · Cho-Jui Hsieh

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #673
in Poster Session 3 »
We study the problem of efficient adversarial attacks on tree based ensembles such as gradient boosting decision trees (GBDTs) and random forests (RFs). Since these models are non-continuous step functions and gradient does not exist, most existing efficient adversarial attacks are not applicable. Although decision-based black-box attacks can be applied, they cannot utilize the special structure of trees. In our work, we transform the attack problem into a discrete search problem specially designed for tree ensembles, where the goal is to find a valid ``leaf tuple'' that leads to mis-classification while having the shortest distance to the original input. With this formulation, we show that a simple yet effective greedy algorithm can be applied to iteratively optimize the adversarial example by moving the leaf tuple to its neighborhood within hamming distance 1. Experimental results on several large GBDT and RF models with up to hundreds of trees demonstrate that our method can be thousands of times faster than the previous mixed-integer linear programming (MILP) based approach, while also providing smaller (better) adversarial examples than decision-based black-box attacks on general $\ell_p$ ($p=1, 2, \infty$) norm perturbations.

Author Information

Chong Zhang (UCLA)
Huan Zhang (UCLA)
Cho-Jui Hsieh (UCLA)

More from the Same Authors