BadMerging: Backdoor Attacks Against Model Merging

Jinghuai Zhang, Jianfeng Chi, Zhehao Li, Kunlin Cai, Yi Zhang, Yuan Tian
July 2024
Cite Code Dataset Video Source Document
Image credit: Unsplash

Abstract

…

Type
Conference paper
Publication
In 31st ACM Conference on Computer and Communications Security (CCS)
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Jinghuai Zhang
Jinghuai Zhang
PhD Student from 23’Fall

I am broadly interested in the machine learning, security, and privacy with a recent focus on the intersection between them.

Jianfeng Chi
Jianfeng Chi
PhD grad in 2022, now Research Scientist at Meta Superintelligence Labs

I am a research scientist at Meta Superintelligence Labs, working on LLM alignment and reasoning. Previously, I obtained my Ph.D. degree in Computer Science from the University of Virginia in 2022, and did research in Machine Learning and Natural Language Processing, with a focus on ML/AI safety.

Kunlin Cai
Kunlin Cai
PhD Student from 21’Fall

My research interests lie in the security and privacy of emerging technologies, including extended reality (XR) and machine learning.

Yuan Tian
Yuan Tian
Associate Professor

My research interests involve security and privacy and their interactions with computer systems, machine learning, and human-computer interaction.