Larger prompt-injection red-team piles can weaken agent defenses
A Qwen3-4B retrained on PISmith’s larger haul was hijacked on 47.5% of unseen stress-test tasks, versus 27.5% for RL-Hammer.
52
A Qwen3-4B retrained on PISmith’s larger haul was hijacked on 47.5% of unseen stress-test tasks, versus 27.5% for RL-Hammer.
On AgentDojo and ASB, defended agents reportedly near zero static attack success while keeping benign task utility.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 951 readers · 1.1K views · 90 reads · all time 211K views