0% Complete
صفحه اصلی
/
بیست و نهمین کنفرانس مهندسی برق ایران
Robust Object Detection Against Adversarial Perturbations with Gabor Filter
نویسندگان :
Mohammad Parsa Karimi
1
Abdollah Amirkhani
2
Shahriar B. Shokouhi
3
1- دانشگاه علم و صنعت ایران
2- دانشگاه علم و صنعت ایران
3- دانشگاه علم و صنعت ایران
کلمات کلیدی :
adversarial attack, deep neural network, robustness, Gabor filter
چکیده :
Adversarial attacks are one of the most critical threats in the machine learning field, which raises doubts about the application of deep neural networks (DNNs). Despite the recent advances in DNNs, the adversarial robustness in DNNs has yet to reach an acceptable level, especially against different kinds of perturbations. In this paper, we aim to enhance the robustness of object detection against adversarial perturbations. To this end, we adversarially train YOLOv3 model with different backbones by means of parameterized Gabor convolutional layers. To assess the robustness of our trained models, we have adopted TOG vanishing, TOG fabrication, and TOG mislabeling adversarial attacks. These perturbations are crafted on PASCAL VOC and MSCOCO datasets to simulate three types of targeted specificity, including object-vanishing, object-fabrication, and object-mislabeling, respectively. Extensive evaluations demonstrate that our model equipped with the Gabor filters gain consideration adversarial robustness in addition to the high generalization performance on clean data.
لیست مقالات
لیست مقالات بایگانی شده
Using a Novel Connection Triangle as a Classifier to Discriminate between Different Faults in the Frequency Response Analysis
Mohammad Hamed Samimi
CT Super-Resolution Using Arbitrary Scale Diffusion Model
Mahsa Nadafi Ghahnavieh - Saeed Masoudnia - Hamid Soltanian-Zadeh
بررسی تاثیر کنترل کنندههای سیستم انتقال جریان مستقیم مبتنی بر مبدلهای منبع ولتاژ با اجزای شبکه قدرت با استفاده از روش تحلیل مدال خطی
علی ضیائی - رضا قاضی - روح الامین زینلی داورانی
Modeling of dielectrophoretic single-stage continuous separation of Escherichia coli K38 in a microfluidic channel
Saeed Saedy - Navid Alaei Sheini - Shahrzad Ajabi
Investigating Validity and Reliability of The Features Extracted by a 5R Vertical Robot for Arm Motion and Learning Assessment
Sarvenaz Bourbour - Fariba Bahrami Boodelalou - Ghorban Taghizadeh
Intelligent Near-Infrared Spectroscopy for Blood Glucose Level Classification
Shahrooz Sharifi - Amirhossein Maddah-Torghabehi - Mohammad-Reza Akbarzadeh-Totonchi
Emotion Recognition from EEG Signals During REM Sleep
Asghar Zarei - Ali Mahmoudi
A High Dynamic Range Differential Rectifier for RF Energy Harvesting
Ataollah Mahsafar - Mohammad Yavari
Impacts of Various Wind Turbine Generators on Transient Recovery Voltage in a Medium Voltage Power Network
Mostafa Heydari - Ali Asghar Razi-Kazemi
Applying Parameter-Oriented Learning to Identify Statistical EEG Features Associated with Depression
Sara Bargi Barkouk - Melika Changizi - Mahdi Zolfagharzadeh Kermani - Ali Asadi Zeidabadi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4