1
Hidden State Poisoning Attacks against Mamba-based Language Models
对Mamba等状态空间模型提出隐藏状态中毒攻击，揭示其对抗鲁棒性重大漏洞，引发对新型LLM安全性的反思。
arXiv:2601.01972v4 Announce Type: cross Abstract: State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language mode…