Inicio  /  Applied Sciences  /  Vol: 13 Par: 7 (2023)  /  Artículo
ARTÍCULO
TITULO

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks

Saqib Ali    
Sana Ashraf    
Muhammad Sohaib Yousaf    
Shazia Riaz and Guojun Wang    

Resumen

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.

 Artículos similares

       
 
Shengkun Gu and Dejiang Wang    
Within the domain of architectural urban informatization, the automated precision recognition of two-dimensional paper schematics emerges as a pivotal technical challenge. Recognition methods traditionally employed frequently encounter limitations due to... ver más
Revista: Information

 
Michal Brzus, Kevin Knoernschild, Jessica C. Sieren and Hans J. Johnson    
Translation of basic animal research to find effective methods of diagnosing and treating human neurological disorders requires parallel analysis infrastructures. Small animals such as mice provide exploratory animal disease models. However, many interve... ver más
Revista: Algorithms

 
Thomas P. Oghalai, Ryan Long, Wihan Kim, Brian E. Applegate and John S. Oghalai    
Optical Coherence Tomography (OCT) is a light-based imaging modality that is used widely in the diagnosis and management of eye disease, and it is starting to become used to evaluate for ear disease. However, manual image analysis to interpret the anatom... ver más
Revista: Algorithms

 
Junwei Chen, Yangze Liang, Zheng Xie, Shaofeng Wang and Zhao Xu    
Building information models (BIMs) offer advantages, such as visualization and collaboration, making them widely used in the management of existing buildings. Currently, most BIMs for existing indoor spaces are manually created, consuming a significant a... ver más
Revista: Applied Sciences

 
Muhammad Nouman Noor, Muhammad Nazir, Sajid Ali Khan, Imran Ashraf and Oh-Young Song    
Globally, gastrointestinal (GI) tract diseases are on the rise. If left untreated, people may die from these diseases. Early discovery and categorization of these diseases can reduce the severity of the disease and save lives. Automated procedures are ne... ver más
Revista: Applied Sciences