Qingni Shen

ScriptChecker: To Tame Third-party Script Execution With Task Capabilities

2022

We present ScriptChecker, a novel browser-based framework to effectively and efficiently restrict third-party script execution according to the host web page's directives. Different from all existing schemes functioning at the JavaScript layer, ScriptChecker holistically harnesses …

NCL: Textual Backdoor Defense Using Noise-Augmented Contrastive Learning

2023

At present, backdoor attacks attract attention as they do great harm to deep learning models. By poisoning the training data, the adversary makes the model trained based on this dataset being injected with a backdoor. …

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

2024 · arXiv (Cornell University)

Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyrights. Membership inference arises in these contexts as a potential …

IPOD2: an irrecoverable and verifiable deletion scheme for outsourced data

2024 · The Computer Journal

Abstract To alleviate the burden of data storage and management, there is a growing trend of outsourcing data to the cloud that enables users to remotely manage their data flexibly. However, this shift also raises …

Privacy-Enhanced Federated Feature Alignment Method Based on Secure Multi-Party Computation

2025 · International Journal of Pattern Recognition and Artificial Intelligence

Federated learning enables collaborative modeling across institutions while preserving data privacy. However, achieving accurate and efficient feature alignment remains a significant challenge, particularly in scenarios with nonoverlapping feature distributions. To address this issue, we propose …