Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks

본문 미리보기

arXiv:2607.25227v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of