Adversarial Example Detection in Deployed Tree Ensembles
Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a user's trust in the model. Typically, approaches try to alleviate this problem by verifying how robust a learned ensemble is or robustifying the learning process. We take an alternative approach and attempt to detect adversarial examples in a post-deployment setting. We present a novel method for this task that works by analyzing an unseen example's output configuration, which is the set of predictions made by an ensemble's constituent trees. Our approach works with any additive tree ensemble and does not require training a separate model. We evaluate our approach on three different tree ensemble learners. We empirically show that our method is currently the best adversarial detection method for tree ensembles.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Faster Repeated Evasion Attacks in Tree Ensembles
Tree ensembles are one of the most widely used model classes. However, these models are susceptible to adversarial examples, i.e., slightly perturbed examples that elicit a misprediction. There has been significant resea…
An Efficient Adversarial Attack for Tree Ensembles
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 d…
Adversarial AttackvalidAn Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection
As cyber-attacks become more sophisticated, improving the robustness of Machine Learning (ML) models must be a priority for enterprises of all sizes. To reliably compare the robustness of different ML models for cyber-at…
Adversarial RobustnessCyber Attack DetectionIntrusion DetectionNetwork Intrusion DetectionBeyond Robustness: Resilience Verification of Tree-Based Classifiers
In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. To mitigate the limitations of robustness, we introduce a ne…
Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification
The Internet of Things (IoT) faces tremendous security challenges. Machine learning models can be used to tackle the growing number of cyber-attack variations targeting IoT systems, but the increasing threat posed by adv…
Adversarial RobustnessBinary ClassificationIntrusion DetectionMulti-class Classification+1