New Prompt Injection Papers: Agents Rule of Two and The Attacker Moves Second

simonwillison.netsite

Simon Willison's Nov 2025 commentary on both landmark papers, including the finding that 12 published defenses were bypassed at >90% success rate using gradient descent and RL-based adaptive attacks.

from

Prompt Injection

added

2026-10-10

likes

0

Prompt Injection › Articles and Blog posts: “Simon Willison's Nov 2025 commentary on both landmark papers, including the finding that 12 published defenses were bypassed at >90% success rate using gradient descent and RL-based adaptive attacks.”