# attack-design
標記為「attack-design」的 2 篇文章
Interpretability-Driven Attack Design
Using interpretability insights to design more effective and targeted attacks on language models.
frontier-researchinterpretabilityattack-designresearch
Interpretability-Driven 攻擊 Design
Using interpretability insights to design more effective and targeted attacks on language models.
frontier-researchinterpretabilityattack-designresearch