Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks
Open Access
- 5 April 2023
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (7) , 4599
Abstract
The successful outcomes of deep learning (DL) algorithms in diverse fields have prompted researchers to consider backdoor attacks on DL models to defend them in practical applications. Adversarial examples could deceive a safety-critical system, which could lead to hazardous situations. To cope with this, we suggested a segmentation technique that makes hidden trigger backdoor attacks more robust. The tiny trigger patterns are conventionally established by a series of parameters encompassing their DNN size, location, color, shape, and other defining attributes. From the original triggers, alternate triggers are generated to control the backdoor patterns by a third party in addition to their original designer, which can produce a higher success rate than the original triggers. However, the significant downside of these approaches is the lack of automation in the scene segmentation phase, which results in the poor optimization of the threat model. We developed a novel technique that automatically generates alternate triggers to increase the effectiveness of triggers. Image denoising is performed for this purpose, followed by scene segmentation techniques to make the poisoned classifier more robust. The experimental results demonstrated that our proposed technique achieved 99% to 100% accuracy and helped reduce the vulnerabilities of DL models by exposing their loopholes.Keywords
Funding Information
- National Key Research and Development Program of China (2020YFB1005804, 61632009, 2016ZJ01)
- National Natural Science Foundation of China (2020YFB1005804, 61632009, 2016ZJ01)
- High-Level Talents Program of Higher Education in Guangdong Province (2020YFB1005804, 61632009, 2016ZJ01)
- NCBC-PAAL, UAF, Faisalabad (2020YFB1005804, 61632009, 2016ZJ01)
This publication has 20 references indexed in Scilit:
- An efficient algorithm to detect DDoS amplification attacksJournal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 2020
- Backdoor Attacks Against Transfer Learning With Pre-Trained Deep Learning ModelsIEEE Transactions on Services Computing, 2020
- Clean-Label Backdoor Attacks on Video Recognition Models2020
- Hidden Trigger Backdoor AttacksProceedings of the AAAI Conference on Artificial Intelligence, 2020
- A Survey on Machine Learning Adversarial AttacksJournal of Information Security and Cryptography (Enigma), 2020
- Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks2019
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- Patch-based models and algorithms for image denoising: a comparative review between patch-based images denoising methods for additive noise reductionEURASIP Journal on Image and Video Processing, 2017
- Membership Inference Attacks Against Machine Learning Models2017
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures2015