AI RESEARCH
CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
arXiv CS.CL
•
ArXi:2603.12206v1 Announce Type: new State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performance. However, Hidden State Poisoning Attacks (HiSPAs), a recently discovered vulnerability that corrupts SSM memory through adversarial strings, pose a critical threat to these architectures and their hybrid variants. Framing the HiSPA mitigation task as a binary classification problem at the token level, we