Orion: Online Backdoor Sample Detection via Evolution Deviance

Authors: Huayang Huang, Qian Wang, Xueluan Gong, Tao Wang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on six attacks, three datasets, and two architectures verify the effectiveness of Orion. It is shown that Orion outperforms state-of-the-art defenses and can identify feature-hidden attacks with an F1-score of 90%, compared to 40% for other detection schemes.
Researcher Affiliation Academia 1Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Hubei, China 2School of Computer Science, Wuhan University, Hubei, China
Pseudocode No No explicit pseudocode or algorithm blocks (e.g., labeled 'Algorithm X' or 'Pseudocode') were found in the paper. The methodology is described in prose.
Open Source Code No The paper does not include any explicit statements about releasing source code for the described methodology or provide a link to a code repository.
Open Datasets Yes We perform experiments on three datasets CIFAR-10, GTSRB and Tiny-Imagenet [Krizhevsky and Hinton, 2009; Stallkamp et al., 2012; Le and Yang, 2015].
Dataset Splits Yes CIFAR-10 and GTSRB have an image size of 32x32 and contain 10 and 43 classes, respectively. CIFAR-10 has 50,000 and 10,000 samples for training and testing. GTSRB contains 39,209 training and 12,630 validation images. Tiny-Imagenet is a subset of Image Net, containing 200 classes. Each class contains 500 training data and 50 test samples.
Hardware Specification Yes All the experiments are carried out on a single NVIDIA Ge Force RTX 3090 GPU.
Software Dependencies No The paper mentions software components like 'Adam optimizer' and model architectures like 'VGG16-bn' and 'Res Net-56', but does not provide specific version numbers for any libraries, frameworks (e.g., PyTorch, TensorFlow), or other software dependencies.
Experiment Setup Yes We adopt the Adam optimizer to train each S-Net for 25 epochs, with a learning rate of 0.001.