11 citations · 60 across the 31 of their papers we have counts for
5 papers · 1 filter
Robust Anti-Backdoor Instruction Tuning in LVLMs
Yuan Xun, Siyuan Liang, Xiaojun Jia +2
Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contami…
Does Few-shot Learning Suffer from Backdoor Attacks?
Xinwei Liu, Xiaojun Jia, Jindong Gu +3
The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored.…
MOVE: Effective and Harmless Ownership Verification via Embedded External Features
Yiming Li, Linghui Zhu, Xiaojun Jia +5
Currently, deep neural networks (DNNs) are widely adopted in different applications. Despite its commercial values, training a well-performing DNN is resource-consuming. Accordingl…
Defending against Model Stealing via Verifying Embedded External Features
Yiming Li, Linghui Zhu, Xiaojun Jia +3
Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adv…
Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples
Xiaojun Jia, Xingxing Wei, Xiaochun Cao +1
Recent research has demonstrated that adding some imperceptible perturbations to original images can fool deep learning models. However, the current adversarial perturbations are u…