Open in app

Sign In

Write

Sign In

Alejandro Mosquera
Alejandro Mosquera

Home

About

Dec 26, 2022

On the Intriguing Properties of Backdoored Neural Networks

Introduction Malicious actors can alter the expected behavior of a neural network in order to respond to data containing certain triggers only known to the attacker, without disrupting model performance when presented with normal inputs. An adversary will commonly force these misclassifications by either performing trigger injection [19] or dataset poisoning…

Neural Trojan Detection

8 min read

On the Intriguing Properties of Backdoored Neural Networks
On the Intriguing Properties of Backdoored Neural Networks
Neural Trojan Detection

8 min read

Alejandro Mosquera

Alejandro Mosquera

Researcher in AI, Cyber Security, Machine Learning, NLP. Opinions are my own. www.amsqr.com www.alejandromosquera.net

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech