Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
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.
Code (1)
Similar Papers 제목 키워드 기반
STIQ: Safeguarding Training and Inferencing of Quantum Neural Networks from Untrusted Cloud
The high expenses imposed by current quantum cloud providers, coupled with the escalating need for quantum resources, may incentivize the emergence of cheaper cloud-based quantum services from potentially untrusted provi…
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long-range techniques and benchmarks and fin…
Malware ClassificationMalware DetectionFew-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network
Deep learning-based methods in computational microscopy have been shown to be powerful but in general face some challenges due to limited generalization to new types of samples and requirements for large and diverse trai…
Image ReconstructionTransfer LearningAssociative Long Short-Term Memory
We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely …
MemorizationRetrievalHybrid Near-Field and Far-Field Localization with Multiple Holographic MIMO Surfaces
Localization methods based on holographic multiple input multiple output (HMIMO) have gained much attention for its potential to achieve high accuracy. By deploying multiple HMIMOs, we can improve the link quality and sy…