Tsinghua Researchers Show Backdoored AI Models Steal 94.9% of Private Training Data
Researchers at Tsinghua show that whoever ships an open-source LLM can plant a backdoor that leaks your private fine-tuning queries with only black-box access.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
Researchers at Tsinghua show that whoever ships an open-source LLM can plant a backdoor that leaks your private fine-tuning queries with only black-box access.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
