Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
arXiv preprint arXiv:2403.09513 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
citing papers explorer
-
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
-
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.