Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy

by   Min Du, et al.

Outlier detection and novelty detection are two important topics for anomaly detection. Suppose the majority of a dataset are drawn from a certain distribution, outlier detection and novelty detection both aim to detect data samples that do not fit the distribution. Outliers refer to data samples within this dataset, while novelties refer to new samples. In the meantime, backdoor poisoning attacks for machine learning models are achieved through injecting poisoning samples into the training dataset, which could be regarded as "outliers" that are intentionally added by attackers. Differential privacy has been proposed to avoid leaking any individual's information, when aggregated analysis is performed on a given dataset. It is typically achieved by adding random noise, either directly to the input dataset, or to intermediate results of the aggregation mechanism. In this paper, we demonstrate that applying differential privacy can improve the utility of outlier detection and novelty detection, with an extension to detect poisoning samples in backdoor attacks. We first present a theoretical analysis on how differential privacy helps with the detection, and then conduct extensive experiments to validate the effectiveness of differential privacy in improving outlier detection, novelty detection, and backdoor attack detection.


page 1

page 2

page 3

page 4


PCOR: Private Contextual Outlier Release via Differentially Private Search

Outlier detection plays a significant role in various real world applica...

Bayesian Differential Privacy for Linear Dynamical Systems

Differential privacy is a privacy measure based on the difficulty of dis...

Empirical Differential Privacy

We show how to achieve differential privacy with no or reduced added noi...

Adversarial Classification under Gaussian Mechanism: Calibrating the Attack to Sensitivity

This work studies anomaly detection under differential privacy with Gaus...

Detecting Anomalous LAN Activities under Differential Privacy

Anomaly detection has emerged as a popular technique for detecting malic...

Differential Privacy of Aggregated DC Optimal Power Flow Data

We consider the problem of privately releasing aggregated network statis...

Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal

An accurate and substantial dataset is necessary to train a reliable and...

Please sign up or login with your details

Forgot password? Click here to reset