Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxes

04/25/2021
by   Changshun Wu, et al.
0

We present an approach for monitoring classification systems via data abstraction. Data abstraction relies on the notion of box with a resolution. Box-based abstraction consists in representing a set of values by its minimal and maximal values in each dimension. We augment boxes with a notion of resolution and define their clustering coverage, which is intuitively a quantitative metric that indicates the abstraction quality. This allows studying the effect of different clustering parameters on the constructed boxes and estimating an interval of sub-optimal parameters. Moreover, we automatically construct monitors that leverage both the correct and incorrect behaviors of a system. This allows checking the size of the monitor abstractions and analyzing the separability of the network. Monitors are obtained by combining the sub-monitors of each class of the system placed at some selected layers. Our experiments demonstrate the effectiveness of our clustering coverage estimation and show how to assess the effectiveness and precision of monitors according to the selected clustering parameter and monitored layers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/20/2019

Outside the Box: Abstraction-Based Monitoring of Neural Networks

Neural networks have demonstrated unmatched performance in a range of cl...
research
06/04/2018

Automatic Clustering of a Network Protocol with Weakly-Supervised Clustering

Abstraction is a fundamental part when learning behavioral models of sys...
research
07/18/2020

AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling

Most state-of-the-art object detection systems follow an anchor-based di...
research
03/15/2022

On Comparable Box Dimension

Two boxes in ℝ^d are comparable if one of them is a subset of a translat...
research
01/16/2013

Likelihood Computations Using Value Abstractions

In this paper, we use evidence-specific value abstraction for speeding B...
research
01/14/2023

Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions

An abstraction can be used to relate two structural causal models repres...
research
08/17/2018

Efficient Single-Shot Multibox Detector for Construction Site Monitoring

Asset monitoring in construction sites is an intricate, manually intensi...

Please sign up or login with your details

Forgot password? Click here to reset