Ling Liu, Fatih Ilhan, Ka-Ho Chow, Wenqi Wei, Yanzhao Wu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learningbased 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 falsepositive rates. The source code is available at https: //github.com/git-disl/STDLens.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.11511")
get_code_for_paper("2303.11511")
have("2303.11511")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.11511.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.11511)
Connect an agent — have() is free.