Backdooring Sparse Autoencoders
Sparse autoencoders (SAEs) are increasingly used not only to interpret language models but also to intervene on their internal representations. We show that this creates a supply-chain attack surface: a maliciously modified SAE can induce attacker-chosen behavior when inserted into the forward pass of an otherwise unch...
E. Ahlers, Daniel Passon, Tobias Kiecker et al.
· 0 citations