21 citations · 29 across the 7 of their papers we have counts for
7 papers · 1 filter
Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks
Xinjian Luo, Hongyan Chang, Jianxin Wei +5
Distributed large language model (LLM) inference frameworks connect isolated consumer-grade devices for large-scale model inference, substantially reducing hardware constraints. Ho…
Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
Hongyan Chang, Ergute Bao, Xinjian Luo +1
Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden ins…
Prompt Inference Attack on Distributed Large Language Model Inference Frameworks
Xinjian Luo, Ting Yu, Xiaokui Xiao
The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To add…
Calibrating Noise for Group Privacy in Subsampled Mechanisms
Yangfan Jiang, Xinjian Luo, Yin Yang +1
Given a group size m and a sensitive dataset D, group privacy (GP) releases information about D with the guarantee that the adversary cannot infer with high confidence whether the…
Passive Inference Attacks on Split Learning via Adversarial Regularization
Xiaochen Zhu, Xinjian Luo, Yuncheng Wu +3
Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong…
A Fusion-Denoising Attack on InstaHide with Data Augmentation
Xinjian Luo, Xiaokui Xiao, Yuncheng Wu +2
InstaHide is a state-of-the-art mechanism for protecting private training images, by mixing multiple private images and modifying them such that their visual features are indisting…