Work

AFI: Blackbox Backdoor Detection Method Based on Adaptive Feature Injection

Year: 2025

Type: article

Abstract: At inference time, deep neural networks are susceptible to backdoor attacks, which can produce attacker-controlled outputs when inputs contain carefully crafted triggers. Existing defense methods often focus on specific attac... | Find, read and cite all the research you need on Tech Science Press

Source: Computers, materials & continua/Computers, materials & continua (Print)

DOI: 10.32604/cmc.2025.073798

Authors: Simin Tang, Zhiyong Zhang, Junyan Pan, Gaoyuan Quan, Weiguo Wang, Junchang Jing

Institutions: Henan University of Science and Technology, Henan Normal University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: National Natural Science Foundation of China

Awards: G5047584957, G8634726384