1 code implementation • 26 Jan 2024 • Peizhuo Lv, Hualong Ma, Kai Chen, Jiachen Zhou, Shengzhi Zhang, Ruigang Liang, Shenchen Zhu, Pan Li, Yingjun Zhang
To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied.
no code implementations • 3 Jan 2023 • Ying Cao, Ruigang Liang, Kai Chen, Peiwei Hu
They formulate the decompilation process as a translation problem between LPL and HPL, aiming to reduce the human cost required to develop decompilation tools and improve their generalizability.
no code implementations • 17 Oct 2022 • Pan Li, Peizhuo Lv, Shenchen Zhu, Ruigang Liang, Kai Chen
Although traditional static DNNs are vulnerable to the membership inference attack (MIA) , which aims to infer whether a particular point was used to train the model, little is known about how such an attack performs on the dynamic NNs.
1 code implementation • 8 Sep 2022 • Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, Chang Yue, Fan Xiang, Yuling Cai, Hualong Ma, Yingjun Zhang, Guozhu Meng
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and Natural Language Processing (NLP) domains.
no code implementations • 9 Jul 2022 • Chang Yue, Peizhuo Lv, Ruigang Liang, Kai Chen
However, most of the triggers used in the current study are fixed patterns patched on a small fraction of an image and are often clearly mislabeled, which is easily detected by humans or defense methods such as Neural Cleanse and SentiNet.
1 code implementation • 22 Nov 2021 • Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang
In this paper, we propose DBIA, a novel data-free backdoor attack against the CV-oriented transformer networks, leveraging the inherent attention mechanism of transformers to generate triggers and injecting the backdoor using the poisoned surrogate dataset.
no code implementations • 25 Mar 2021 • Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Yue Zhao, Yingjiu Li
Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs.
no code implementations • 26 Dec 2018 • Yue Zhao, Hong Zhu, Ruigang Liang, Qintao Shen, Shengzhi Zhang, Kai Chen
In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors.