لطفا منتظر بمانید ...
0% Complete
English
صفحه اصلی
/
شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Detection of Backdoor Attacks in Neural Networks Using Input Optimization
نویسندگان :
Parsa Hashemi Khorsand
1
Ahmad Nickabadi
2
1- Amirkabir University of Technology (Tehran Polytechnic)
2- Amirkabir University of Technology (Tehran Polytechnic)
کلمات کلیدی :
backdoor attacks،adversarial robustness،backdoor detection،model contamination detection،input optimization،regularization
چکیده :
This paper presents a clean-data-free framework for detecting backdoor attacks in neural networks via input optimization. We introduce two complementary strategies. First, joint input optimization with a cleanliness detector: for each label, we optimize an input that simultaneously (i) maximizes the target-label logit on the suspected model and (ii) maintains in-domain naturalness according to an auxiliary diagnostic model; the resulting patterns are then inspected for trigger-like artifacts. Second, input optimization with the largest feasible regularization coefficient: for each label, we find the largest feasible regularization coefficient that still attains a preset confidence threshold, forming a per-class signature vector; Median Absolute Deviation (MAD) is then used to flag outlier labels as compromised. On MNIST, our framework achieves 89.5 percent detection accuracy on backdoored models with 100 percent recall in poisoned-label flagging, while requiring no access to clean training data. We further compare our methods with Neural Cleanse and the Certified Backdoor Detector (CBD).
لیست مقالات
لیست مقالات بایگانی شده
IoMT-Enabled Smart Healthcare: State-of-the-Art, Security and Future Directions
Shivam Tripathi - Vatsalkumar Makwana - Malaram Kumhar - Harshal Trivedi - Jitendra Bhatia - Sudeep Tanwar - Hossein Shahinzadeh
A Blockchain Architecture for Secure, High-Speed P2P Energy Trades with Game-Theoretic Coalition Formation
Amin Aboutalebi Najafabadi - Seyed Hossein Hosseinian
بررسی تأثیر استقرار استاندارد COBIT در افزایش بهره وری سازمانها (مطالعه موردی: شعب نمایندگیهای همراه اول، ایرانسل، رایتل)
دکتر محمد ابراهیم سمیع - ساره رحمانیان محمد ابراهیم سمیع - ساره رحمانیان -
The risk prediction of heart disease by using neuro-fuzzy and improved GOA
Vahid Safari Dehnavi - Masoud Shafiee
To Kill a Mockingbird: Cryptanalysis of an Authenticated Key Exchange Scheme for Drones
Neda Toghraee - Hamid Mala
Advanced SMS Spam Detection using Deep Complex Models and Sine-Cosine Algorithm
Sepehr Rezaei - Mohammadreza Shams - Mohsen Alambardar Meybodi
ارائۀ چارچوب هستانشناسی برای شهر هوشمند مبتنی بر سیستمهای سایبر-فیزیکی
علی اصغر قائمی - جعفر حبیبی - سید حسن میریان
A Topic Based Method to Classify the Question Clarity in CQA Networks
Alireza Khabbazan - Dr Ahmad Ali Abin
Inner and Outer Bearing Fault Diagnosis of electrical Motors Using a Proposed Algorithm and Vibration Signals
Vahid Safari Dehnavi - Masoud Shafiee
پیش بینی بیماری قلبی با استفاده از روش تحلیل شبکه ای
هدیه مشتاقی محمدزاده - فاطمه باقری
بیشتر
ثمین همایش، سامانه مدیریت همایش ها و جشنواره ها - نگارش 45.0.1