Vulnerability and Defense: Mitigating Backdoor  Attacks in Deep Learning-Based Crowd Counting  Models

Luo, Jinzi

Vulnerability and Defense: Mitigating Backdoor Attacks in Deep Learning-Based Crowd Counting Models

Luo, Jinzi (2025) Vulnerability and Defense: Mitigating Backdoor Attacks in Deep Learning-Based Crowd Counting Models. In: Proceedings of the 4th International Conference on Computing Innovation and Applied Physics, CONF-CIAP 2025, 17-23 January 2025, Eskişehir, Turkey.

PDF
71890.pdf
Download (897kB)

Abstract

Crowd counting aims to infer the number of people or objects in an image
through different methods. It is widely used in surveillance, sensitive events, etc., and
plays a vital role in a series of security- critical applications. Most of the state-of-the-art
crowd counting models are based on dee

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Date Deposited:	04 Mar 2026 18:27
Last Modified:	16 Apr 2026 21:37
URI:	http://eprints.eai.eu/id/eprint/52569

Actions (login required)

: View Item