TrojanNet: Embedding Hidden Trojan Horse Models in Neural Networks

02/24/2020
by   Chuan Guo, et al.
0

The complexity of large-scale neural networks can lead to poor understanding of their internal details. We show that this opaqueness provides an opportunity for adversaries to embed unintended functionalities into the network in the form of Trojan horses. Our novel framework hides the existence of a Trojan network with arbitrary desired functionality within a benign transport network. We prove theoretically that the Trojan network's detection is computationally infeasible and demonstrate empirically that the transport network does not compromise its disguise. Our paper exposes an important, previously unknown loophole that could potentially undermine the security and trustworthiness of machine learning.

READ FULL TEXT
research
10/07/2021

Score-based Generative Neural Networks for Large-Scale Optimal Transport

We consider the fundamental problem of sampling the optimal transport co...
research
06/14/2018

Hardware Trojan Attacks on Neural Networks

With the rising popularity of machine learning and the ever increasing d...
research
08/22/2022

An anomaly detection approach for backdoored neural networks: face recognition as a case study

Backdoor attacks allow an attacker to embed functionality jeopardizing p...
research
03/04/2021

Clusterability in Neural Networks

The learned weights of a neural network have often been considered devoi...
research
07/01/2019

On Symmetry and Initialization for Neural Networks

This work provides an additional step in the theoretical understanding o...
research
01/13/2016

Transit directions at global scale

A novel approach to integrated ground and air public transport journey p...
research
10/12/2019

Model Fusion via Optimal Transport

Combining different models is a widely used paradigm in machine learning...

Please sign up or login with your details

Forgot password? Click here to reset