TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals
cs.CR
Submitted: 2026-05-08
Updated: 2026-08-27
Terminology
Sources
- Conditional Computation in Neural Networks for faster models
- How Query Distribution Knowledge Breaks Multidimensional Encrypted Range Queries, With Guarantees
- Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
- ObliDB: Oblivious Query Processing for Secure Databases
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Data Leakage via Access Patterns of Sparse Features in Deep Learning-based Recommendation Systems
- Chiron: Privacy-preserving Machine Learning as a Service
- Adam: A Method for Stochastic Optimization
- Reformer: The Efficient Transformer
- Deep Learning Recommendation Model for Personalization and Recommendation Systems
- 3LegRace: Privacy-Preserving DNN Training over TEEs and GPUs
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs