AI Dynamics

Global AI News Aggregator

About

LLM post-training pipelines vulnerable to combined data poisoning attacks

Feeling safe against data poisoning in post-training? Think again! Individual components of LLM post-training pipelines are surprisingly robust to data poisoning attacks. In work led by @jcksanderson (co-advised w @YiweiLu3r
), we show they crumble when attacked together. 1/n

→ View original post on X — @thegautamkamath