MAAG: A Multi-Attention Architecture for Generalizable Multi-Target Adversarial Attacks
Source abstract
Abstract
Adversarial examples pose a severe threat to deep neural networks. They are crafted by applying imperceptible perturbations to benign inputs, causing the model to produce incorrect predictions. Most existing attack methods exhibit limited generalization, especially in black-box settings involving unseen models or unknown classes. To address these limitations, we propose MAAG (multi-attention adversarial generation), a novel model architecture that enhances attack generalizability and transferability. MAAG integrates channel and spatial attention to extract representative features for adversarial example generation and capture diverse decision boundaries for better transferability. A composite loss guides the generation of adversarial examples across different victim models. Extensive experiments validate the superiority of our proposed method in crafting adversarial examples for both known and unknown classes. Specifically, it surpasses existing generative methods by approximately 7.0% and 7.8% in attack success rate on known and unknown classes, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Adversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Jishou University, Jishou 416000, China
References (58)
Show source-provided references
1. Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv.
2. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
3. Artificial Intelligence Image Recognition Method Based on Convolutional Neural Network Algorithm10.1109/ACCESS.2020.3006097 ↗
4. Application of deep learning-based natural language processing in multilingual sentiment analysis
5. Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc.
6. A varying-parameter complementary neural network for multi-robot tracking and formation via model predictive control10.1016/j.neucom.2024.128384 ↗
7. Recurrent Neural Network for Kinematic Control of Redundant Manipulators With Periodic Input Disturbance and Physical Constraints10.1109/TCYB.2018.2859751 ↗
8. Inter-robot management via neighboring robot sensing and measurement using a zeroing neural dynamics approach10.1016/j.eswa.2023.122938 ↗
9. Novel Snap-Layer MMPC Scheme via Neural Dynamics Equivalency and Solver for Redundant Robot Arms With Five-Layer Physical Limits10.1109/TNNLS.2024.3351674 ↗
10. A deep learning-based approach for emotional analysis of sports dance10.7717/peerj-cs.1441 ↗
11. Deep learning-based signal-to-noise ratio estimation using constellation diagrams
12. DCDLN: A densely connected convolutional dynamic learning network for malaria disease diagnosis10.1016/j.neunet.2024.106339 ↗
13. Neural Networks for Portfolio Analysis in High-Frequency Trading10.1109/TNNLS.2023.3311169 ↗
14. Convolutional Dynamically Convergent Differential Neural Network for Brain Signal Classification10.1109/TNNLS.2024.3437676 ↗
15. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2014). Intriguing properties of neural networks. arXiv.
16. Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., and Swami, A. (2016, January 21–24). The Limitations of Deep Learning in Adversarial Settings. Proceedings of the 2016 IEEE European Symposium on Security and Privacy (EuroS&P), Saarbruecken, Germany.10.1109/EuroSP.2016.36 ↗
17. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2015). Explaining and Harnessing Adversarial Examples. arXiv.
18. Carlini, N., and Wagner, D. (2017, January 22–26). Towards Evaluating the Robustness of Neural Networks. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.10.1109/SP.2017.49 ↗
19. A Variable-Parameter Noise-Tolerant Zeroing Neural Network for Time-Variant Matrix Inversion With Guaranteed Robustness10.1109/TNNLS.2020.3042761 ↗
20. A Segmented Variable-Parameter ZNN for Dynamic Quadratic Minimization With Improved Convergence and Robustness10.1109/TNNLS.2021.3106640 ↗
21. Kurakin, A., Goodfellow, I.J., and Bengio, S. (2018). Adversarial Examples in the Physical World. Artificial Intelligence Safety and Security, Chapman and Hall/CRC.10.1201/9781351251389-8 ↗
22. Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2019). Towards Deep Learning Models Resistant to Adversarial Attacks. arXiv.
23. Tan, Y., and Shi, Y. Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN. Proceedings of the Data Mining and Big Data.
24. Poursaeed, O., Katsman, I., Gao, B., and Belongie, S. (2018, January 18–22). Generative Adversarial Perturbations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00465 ↗
25. Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., and Hassner, T. Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks. Proceedings of the Computer Vision—ECCV 2022.10.1007/978-3-031-19800-7 ↗
26. Generative adversarial networks10.1145/3422622 ↗
27. Han, J., Dong, X., Zhang, R., Chen, D., Zhang, W., Yu, N., Luo, P., and Wang, X. (November, January 27). Once a man: Towards multi-target attack via learning multi-target adversarial network once. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
28. Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., and Varol, G. Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection. Proceedings of the Computer Vision—ECCV 2024.
29. Dong, Y., Liao, F., Pang, T., Su, H., Zhu, J., Hu, X., and Li, J. (2018, January 18–22). Boosting adversarial attacks with momentum. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00957 ↗
30. Xiao, C., Li, B., Zhu, J.Y., He, W., Liu, M., and Song, D. (2019). Generating Adversarial Examples with Adversarial Networks. arXiv.10.24963/ijcai.2018/543 ↗
31. Huang, C., Kairouz, P., Chen, X., Sankar, L., and Rajagopal, R. (2019). Generative Adversarial Privacy. arXiv.
32. Xie, C., Zhang, Z., Zhou, Y., Bai, S., Wang, J., Ren, Z., and Yuille, A.L. (2019, January 15–20). Improving transferability of adversarial examples with input diversity. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00284 ↗
33. Naseer, M., Ranasinghe, K., Khan, S., Khan, F.S., and Porikli, F. (2022). On Improving Adversarial Transferability of Vision Transformers. arXiv.
34. Jia, X., Zhang, Y., Wu, B., Ma, K., Wang, J., and Cao, X. (2022, January 18–24). LAS-AT: Adversarial Training With Learnable Attack Strategy. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01304 ↗
35. Kurakin, A., Goodfellow, I., and Bengio, S. (2017). Adversarial Machine Learning at Scale. arXiv.
36. Xie, C., Wu, Y., Maaten, L.v.d., Yuille, A.L., and He, K. (2019, January 15–20). Feature denoising for improving adversarial robustness. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00059 ↗
37. Guo, C., Rana, M., Cisse, M., and van der Maaten, L. (2018). Countering Adversarial Images using Input Transformations. arXiv.
38. Samangouei, P., Kabkab, M., and Chellappa, R. (2018). Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models. arXiv.
39. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
40. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
41. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
42. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017, January 4–9). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11231 ↗
43. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
44. Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
45. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
46. Mao, X., Qi, G., Chen, Y., Li, X., Duan, R., Ye, S., He, Y., and Xue, H. (2022, January 18–24). Towards Robust Vision Transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01173 ↗
47. Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., and McDaniel, P. (2020). Ensemble Adversarial Training: Attacks and Defenses. arXiv.
48. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
49. Loshchilov, I., and Hutter, F. (2019). Decoupled Weight Decay Regularization. arXiv.
50. Wei, Z., Chen, J., Wu, Z., and Jiang, Y.G. (2023, January 18–22). Enhancing the Self-Universality for Transferable Targeted Attacks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.01182 ↗
51. Liang, K., Dai, X., Li, Y., Wang, D., and Xiao, B. (2025, January 11–15). Improving Transferable Targeted Attacks with Feature Tuning Mixup. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR52734.2025.02403 ↗
52. Naseer, M., Khan, S., Hayat, M., Khan, F.S., and Porikli, F. (2021, January 10–17). On Generating Transferable Targeted Perturbations. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00761 ↗
53. Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., and Varol, G. CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks. Proceedings of the Computer Vision—ECCV 2024.10.1007/978-3-031-72980-5 ↗
54. Vedaldi, A., Bischof, H., Brox, T., and Frahm, J.M. Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting. Proceedings of the Computer Vision—ECCV 2020.
55. Dong, Y., Pang, T., Su, H., and Zhu, J. (2019, January 15–20). Evading defenses to transferable adversarial examples by translation-invariant attacks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00444 ↗
56. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
57. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18–22). The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00068 ↗
58. On Calibration of Modern Neural Networks