DeepAI AI Chat
Log In Sign Up

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

by   Mohammad Mahmudul Alam, et al.

Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common. If the third party is not fully trusted, it is desirable to obfuscate the nature of the inputs and outputs, so that the third party can not easily determine what specific task is being performed. Provably secure protocols for leveraging an untrusted party exist but are too computational demanding to run in practice. We instead explore a different strategy of fast, heuristic security that we call Connectionist Symbolic Pseudo Secrets. By leveraging Holographic Reduced Representations (HRR), we create a neural network with a pseudo-encryption style defense that empirically shows robustness to attack, even under threat models that unrealistically favor the adversary.


page 4

page 19

page 20

page 21

page 22

page 23

page 26

page 27


Quantum preprocessing for information-theoretic security in two-party computation

In classical two-party computation, a trusted initializer who prepares c...

CheckNet: Secure Inference on Untrusted Devices

We introduce CheckNet, a method for secure inference with deep neural ne...

Secure Two-Party Feature Selection

In this work, we study how to securely evaluate the value of trading dat...

Backdoor Attack against NLP models with Robustness-Aware Perturbation defense

Backdoor attack intends to embed hidden backdoor into deep neural networ...

Using Deep Neural Networks to Translate Multi-lingual Threat Intelligence

The multilingual nature of the Internet increases complications in the c...

On the Composability of Statistically Secure Random Oblivious Transfer

We show that stand-alone statistically secure random oblivious transfer ...

ARTEMIS: Neutralizing BGP Hijacking within a Minute

BGP prefix hijacking is a critical threat to Internet organizations and ...

Code Repositories


Research code for heuristically hiding information for inference run on 3rd party systems

view repo