# STDLens: Model Hijacking-Resilient Federated Learning for Object Detection

arXiv: https://arxiv.org/abs/2303.11511 · HTML: https://mlsanity.com/paper/2303.11511/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Can You Really Backdoor Federated Learning?](https://mlsanity.com/paper/1911.07963/) (2019)
- [Detecting AI Trojans Using Meta Neural Analysis](https://mlsanity.com/paper/1910.03137/) (2019)
- [CRFL: Certifiably Robust Federated Learning against Backdoor Attacks](https://mlsanity.com/paper/2106.08283/) (2021)
- [FLOP: Federated Learning on Medical Datasets using Partial Networks](https://mlsanity.com/paper/2102.05218/) (2021)
- [FLAME: Taming Backdoors in Federated Learning (Extended Version 1)](https://mlsanity.com/paper/2101.02281/) (2021)
- [Get a Model! Model Hijacking Attack Against Machine Learning Models](https://mlsanity.com/paper/2111.04394/) (2021)
- [Federated Learning in Adversarial Settings](https://mlsanity.com/paper/2010.07808/) (2020)

## Built on by (most cited first, 4 of 4)

- [Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance](https://mlsanity.com/paper/2402.01096/) (2024)
- [On the Efficiency of Privacy Attacks in Federated Learning](https://mlsanity.com/paper/2404.09430/) (2024)
- [Data Poisoning and Leakage Analysis in Federated Learning](https://mlsanity.com/paper/2409.13004/) (2024)
- [Osmosis Distillation: Model Hijacking with the Fewest Samples](https://mlsanity.com/paper/2603.04859/) (2026)

## Abstract (arXiv)

Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clients. Despite its advantages, FL is vulnerable to model hijacking. The attacker can control how the object detection system should misbehave by implanting Trojaned gradients using only a small number of compromised clients in the collaborative learning process. This paper introduces STDLens, a principled approach to safeguarding FL against such attacks. We first investigate existing mitigation mechanisms and analyze their failures caused by the inherent errors in spatial clustering analysis on gradients. Based on the insights, we introduce a three-tier forensic framework to identify and expel Trojaned gradients and reclaim the performance over the course of FL. We consider three types of adaptive attacks and demonstrate the robustness of STDLens against advanced adversaries. Extensive experiments show that STDLens can protect FL against different model hijacking attacks and outperform existing methods in identifying and removing Trojaned gradients with significantly higher precision and much lower false-positive rates.