This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

The paper addresses the vulnerability of CKKS-based Fully Homomorphic Encryption (FHE) to overflow attacks by proposing a formal verification technique that guarantees certified bounds on all neuron r…

The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.

This paper provides a comparative analysis and benchmarking of Secure Multi-Party Computation (SMPC) and Fully Homomorphic Encryption (FHE) for machine learning, finding that the optimal choice depend…

This paper presents an efficient fault-tolerance scheme for CPU-based fully homomorphic encryption (FHE) that reduces protection overhead and achieves 100 percent detection rate under random single-bi…

SecureRouter is an encrypted routing and inference framework that accelerates secure transformer inference by adaptively selecting the optimal model size based on the encrypted input, achieving a 1.95…

This paper evaluates the vulnerability of Fully Homomorphic Encryption (FHE) computation to silent data corruption (SDC) using large-scale fault-injection experiments and theoretical analysis.

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

This paper characterizes per-bit-position fault sensitivity in machine learning inference across various workloads and floating-point formats, identifying a sharp bit-sensitivity transition and derivi…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

The paper proposes a decision-aware quadratic replacement for the ReLU activation function, enabling low-degree, calibration-lossless polynomial approximations for neural network inference under Fully…

The paper demonstrates that standard homomorphic encryption (HE) schemes are insufficient to guarantee integrity in networked control systems (NCS) against covert attacks, proposing instead a verifiab…

The paper proposes a co-design paradigm, 'Meeting in the Middle,' to make Fully Homomorphic Encryption (FHE) practical for AI inference by optimizing both the cryptographic schemes and the underlying…

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

The paper introduces SecRL-Prune, a structured reinforcement learning framework that effectively prunes CodeLLMs while preserving their critical ability to generate adversarial, functionality-preservi…

The paper introduces Fine-Tuning Integrity (FTI), a security goal that uses Succinct Model Difference Proofs (SMDPs) to cryptographically prove that a fine-tuned model update adheres to specific struc…

TENNOR is a system that enables efficient and private training of wide neural networks in untrusted cloud environments by using doubly oblivious primitives and a novel memory-efficient hashing scheme.

AEGIS is a novel system that significantly improves the scalability of running large, long-sequence Transformer models under Fully Homomorphic Encryption (FHE) on multi-GPU systems by optimizing data…

The paper introduces a novel public key encryption scheme with high security by leveraging the conjectured intractability of two types of highly corrupted constraint satisfaction problems (CSPs).