Papers by Shangguang Wang
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi
| Challenge: | Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability . |
| Approach: | They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval . |
| Outcome: | The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets. |
Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models (2026.acl-long)
Copied to clipboard
Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin, Linjie Zhu, Hongke Fu, Shangguang Wang, Tao Qi
| Challenge: | Existing methods assess model memorization of key semantic concepts within a video but do not provide reliable evidence that a specific video was used during training. |
| Approach: | They propose a black-box MIA framework that can provide reliable evidence of specific video data usage for training multimodal large language models. |
| Outcome: | The proposed framework can provide reliable evidence of specific video data usage for training multimodal large language models. |
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption (2026.acl-long)
Copied to clipboard
Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu, Ziqin Wang, Wanchun Ni, Shangguang Wang, Tao Qi
| Challenge: | Membership inference attacks are a promising tool for auditing training data of LLMs . existing methods rely on the assumption that LLM's assign higher confidence scores to training samples than to non-training ones. |
| Approach: | They propose a membership inference framework that can be robust against adversarial MIAs. |
| Outcome: | The proposed framework can be robust against adversarial MIA methods and AIGT detectors while maintaining the performance of baselines. |