FACADE: A Framework for Adversarial Circuit Anomaly Detection and Evaluation

by   Dhruv Pai, et al.

We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE aims to generate probabilistic distributions over circuits, which provide critical insights to their contribution to changes in the manifold properties of pseudo-classes, or high-dimensional modes in activation space, yielding a powerful tool for uncovering and combating adversarial attacks. Our approach seeks to improve model robustness, enhance scalable model oversight, and demonstrates promising applications in real-world deployment settings.


page 1

page 2

page 3


Security of Machine Learning-Based Anomaly Detection in Cyber Physical Systems

In this study, we focus on the impact of adversarial attacks on deep lea...

Lightweight Collaborative Anomaly Detection for the IoT using Blockchain

Due to their rapid growth and deployment, the Internet of things (IoT) h...

Adversarial Machine Learning Attacks Against Video Anomaly Detection Systems

Anomaly detection in videos is an important computer vision problem with...

Improved Detection of Adversarial Attacks via Penetration Distortion Maximization

This paper is concerned with the defense of deep models against adversar...

Unsupervised Anomaly Detection via Deep Metric Learning with End-to-End Optimization

We investigate unsupervised anomaly detection for high-dimensional data ...

A Simple Unified Framework for Anomaly Detection in Deep Reinforcement Learning

Abnormal states in deep reinforcement learning (RL) are states that are ...

Discovering Imperfectly Observable Adversarial Actions using Anomaly Detection

Anomaly detection is a method for discovering unusual and suspicious beh...

Please sign up or login with your details

Forgot password? Click here to reset