2022-06-28-alam22a.md

title	booktitle	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations	Proceedings of the 39th International Conference on Machine Learning	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 <em>Connectionist Symbolic Pseudo Secrets</em>. By leveraging Holographic Reduced Representations (HRRs), 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.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	alam22a	0	Deploying Convolutional Networks on Untrusted Platforms Using 2{D} Holographic Reduced Representations	367	393	367-393	367	false	Alam, Mohammad Mahmudul and Raff, Edward and Oates, Tim and Holt, James	given family Mohammad Mahmudul Alam given family Edward Raff given family Tim Oates given family James Holt	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/alam22a/alam22a.pdf