CapLite blocks prompt-injection writes without model-written security artifacts
No attack succeeded in 13,935 attacked AgentDojo episodes, with utility under attack of 29.0% versus CaMeL's 27.2%.
62
No attack succeeded in 13,935 attacked AgentDojo episodes, with utility under attack of 29.0% versus CaMeL's 27.2%.
Introduces DRIFT, a black-box attack removing diffusion watermarks by deflecting generative trajectories, achieving 98-100% success across nine watermarking schemes.
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 966 readers · 1.1K views · 90 reads · all time 211K views