Understanding Model Ensemble in Transferable Adversarial Attack

Authors: Wei Yao, Zeliang Zhang, Huayi Tang, Yong Liu

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, extensive experiments with 54 models validate our theoretical framework, representing a significant step forward in understanding transferable model ensemble adversarial attacks.
Researcher Affiliation Academia 1Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China 2Beijing Key Laboratory of Research on Large Models and Intelligent Governance 3Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE 4Independent Researcher. Contributed ideas during the author s B.S. studies at Huazhong University of Science and Technology, Wuhan, China. Correspondence to: Yong Liu <EMAIL>.
Pseudocode No The paper describes methods using mathematical formulations and textual explanations but does not include any clearly labeled pseudocode blocks or algorithm listings.
Open Source Code No The paper does not contain an explicit statement about open-sourcing the code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes We conduct our experiments on three datasets, including the MNIST (Le Cun, 1998), Fashion-MNIST (Xiao et al., 2017), and CIFAR-10 (Krizhevsky et al., 2009) datasets.
Dataset Splits No The paper mentions training on MNIST, Fashion-MNIST, and CIFAR-10, and using these to attack a ResNet-18. It specifies batch size and epochs, but does not provide explicit training, validation, or test dataset splits or refer to standard splits with citations for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU models, CPU types, or memory specifications) used for running the experiments. It only refers to 'deep neural networks' and 'models'.
Software Dependencies No The paper mentions using MI-FGSM, SVRE, and SIA attack methods and the Adam optimizer, but it does not specify any software libraries or frameworks with their version numbers (e.g., PyTorch 1.x, TensorFlow 2.x, Python 3.x).
Experiment Setup Yes For models trained on MNIST, Fashion-MNIST, we set the number of epochs as 10. For models trained on CIFAR-10, we set the number of epochs as 30. We use the Adam optimizer with setting the learning rate as 10e-3. We set the batch size as 64.