SOURCE-LINKED INTELLIGENCE

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents, and emails. Prior work has shown that, in the text domain, black-box prompt injection can achieve near-perfect attack success rates (ASRs). In the image domain, however, existing visual prompt injection methods are substantially less effective in attacking frontier commercial VLMs for materially harmful behavior. Achieving such outputs is hard because it requires a long and/or format-compliant target string, such as a precise, parseable native t

Read original source ↗ Open in workspace

recordType

paper

region

Global