AI RESEARCH
Hidden State Poisoning Attacks against Mamba-based Language Models
arXiv CS.CL
•
ArXi:2601.01972v3 Announce Type: replace State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their adversarial robustness remains critically unexplored. This paper studies the phenomenon whereby specific short input phrases induce a partial amnesia effect in such models, by irreversibly overwriting information in their hidden states, referred to as a Hidden State Poisoning Attack (Hi