Ziqi Zhang

ReMoS

2022 · Proceedings of the 44th International Conference on Software Engineering

Transfer learning is a popular software reuse technique in the deep learning community that enables developers to build custom models (students) based on sophisticated pretrained models (teachers). However, like vulnerability inheritance in traditional software reuse, …

Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression

2024 · arXiv (Cornell University)

We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing demonstrations, without …

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models

2024 · arXiv (Cornell University)

Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's computation speed …

LLMGuard : Safeguarding Real-Time Inference for Large Language Models on Edge Devices

2026 · ACM Transactions on Software Engineering and Methodology

TEE-shielded secure inference offers an efficient solution to protect valuable edge-deployed models from potential thefts. Nevertheless, existing methods are lack of theoretical security analysis, failing to achieve the optimal security. Furthermore, while feasible for small …