FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases


Chong Fu, Xuhong Zhang, and Shouling Ji, Zhejiang University; Ting Wang, Pennsylvania State University; Peng Lin, Chinese Aeronautical Establishment; Yanghe Feng, National University of Defense Technology; Jianwei Yin, Zhejiang University


Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the trojaned model will have attacker-chosen abnormal behavior. Although many backdoor detection methods exist, most of them assume that the defender has access to a set of clean validation samples or samples with the trigger, which may not hold in some crucial real-world cases, e.g., the case where the defender is the maintainer of model-sharing platforms. Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger. The evaluation results on diverse datasets and model architectures show that FreeEagle is effective against various complex backdoor attacks, even outperforming some state-of-the-art non-data-free backdoor detection methods.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

@inproceedings {287097,
author = {Chong Fu and Xuhong Zhang and Shouling Ji and Ting Wang and Peng Lin and Yanghe Feng and Jianwei Yin},
title = {{FreeEagle}: Detecting Complex Neural Trojans in {Data-Free} Cases},
booktitle = {32nd USENIX Security Symposium (USENIX Security 23)},
year = {2023},
isbn = {978-1-939133-37-3},
address = {Anaheim, CA},
pages = {6399--6416},
url = {},
publisher = {USENIX Association},
month = aug

Presentation Video