Alam, Mohammad MahmudulRaff, EdwardOates, TimHolt, James2022-07-142022-07-142022-06-13https://doi.org/10.48550/arXiv.2206.05893http://hdl.handle.net/11603/25154Proceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022.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.27 pagesen-USThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.Text