Machine Learning Algorithms & Natural Language Processing

Feb 16, 2026 · Artificial Intelligence

How ICML 2026 Used Prompt Injection to Trap Automated Reviewers

Reviewers discovered hidden text in ICML 2026 PDFs that injects specific phrases into large‑language‑model generated reviews, turning an attack technique into a defense mechanism and prompting new safeguards such as watermarking and OCR‑based checks.