Analyzing And Editing Inner Mechanisms Of Backdoored Language Models

#ResearchHighlights

"We can successfully insert a weak backdoor mechanism in the benign model, even without also editing the embeddings of the trigger words."

"Our framework can reverse-engineer backdoor mechanisms in toy and large models for the first time, scale the strength of the backdoor mechanism ..."

https://arxiv.org/abs/2302.12461

#ai #llm #pcpablation #mlp #toymodel #largemodel #backdoor #backdooredlanguagemodel #chatgpt