SnapGuard detects prompt injection attacks on screenshot-based web agents via visual stability indicators and contrast-polarity textual signals, reaching F1 0.75 while running 8x faster than GPT-4o with no added memory cost.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.
citing papers explorer
-
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
SnapGuard detects prompt injection attacks on screenshot-based web agents via visual stability indicators and contrast-polarity textual signals, reaching F1 0.75 while running 8x faster than GPT-4o with no added memory cost.
-
Attention Grounded Enhancement for Visual Document Retrieval
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.