Year: 2025
Type: preprint
Abstract: Backdoor attacks embed a hidden functionality into deep neural networks, causing the network to display anomalous behavior when activated by a predetermined pattern in the input Trigger, while behaving well otherwise on public test data. Recent works have shown that backdoored face recognition (FR) systems can respond to natural-looking triggers like a particular pair of sunglasses. Such attacks pose a serious threat to the applicability of FR systems in high-security applications. We propose a novel technique to (1) detect whether an FR network is compromised with a natural, physically realizable trigger, and (2) identify such triggers given a compromised network. We demonstrate the effectiveness of our methods with a compromised FR network, where we are able to identify the trigger (e.g., green sunglasses or red hat) with a top-5 accuracy of 74%, whereas a naive brute force baseline achieves 56% accuracy.
Source: arXiv (Cornell University)
Authors: Raj, Ankita, Pal, Ambar, Arora, Chetan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414684111
Cites:
Cited by:
Related to: