Papers

• Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models (2026)
  Malikeh Ehghaghi et al.
  1.94
• Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models (2025)
  Thomas Winninger et al.
  1.28
• Can LLMs Follow Simple Rules? (2023)
  Norman Mu et al.
  —