Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for misclassification) and adversarial jailbreaks (for harmful output generation), adversarial smuggling exploits the Human-AI capability gap. It encodes harmful content into human-readable visual formats that remain AI-unreadable, thereby evading automated detection and enabling the dissemination of harmful content. We classify smuggling attacks into two pathways: (1) Perceptual Blindness, disrupting text recognition; and (2) Reasoning Blockade, inhibiting semantic un...
| Authors | Zhiheng Li, Zongyang Ma, Yuntong Pan et al. |
|---|---|
| Primary category | cs.CV |
| Published | 8 April 2026 |
| Last updated at source | 9 April 2026 |
Models and datasets referencing this paper
- zhihengli-casia/smugglebenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.