Erase the Injected Region: Multimodal Prompt-Injection Defense with On-Policy Self-Distillation
TL;DR
ERASE, an on-policy self-distillation method that constructs its reference by erasing the injected region in place, is proposed, an on-policy self-distillation method that constructs its reference by erasing the injected region in place.
Abstract
Multimodal indirect prompt injection embeds malicious instructions in external media that also contains information needed for the user's task. Existing defenses can block the attack yet impair the model's use of that information, leaving a gap between attack defense and task preservation. We propose ERASE, an on-policy self-distillation method that constructs its reference by erasing the injected region in place. Modality-appropriate blank content replaces the injection while the surrounding media is preserved. A student reading attacked media learns from a frozen base model reading the erased view through full-distribution token-level feedback on its own rollouts. Across image, audio, and video on two model sizes, ERASE records near-zero observed attack success on the evaluated benchmark while retaining task utility close to the undefended clean-input level. On 3B audio, ERASE reaches 60.1% attacked-input accuracy compared with ARGUS's 33.1%, within 0.5 points of the undefended clean-input level. Experiments show that ERASE reduces injection dependence from 6.26 to 0.0095 on 3B audio while staying close to the base model on the erased input. Out-of-domain accuracy also stays near the base level. Our code will be made publicly available upon acceptance.
