Jailbreak vulnerability in MLLMs is language- and modality-dependent, producing rank reversals in model safety between English and Spanish conditions.
Foot-in-the-door: A multi-turn jailbreak for llms
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
years
2026 3representative citing papers
A single safety demonstration appended at inference time mitigates many-shot jailbreak attacks by counteracting implicit malicious fine-tuning on harmful examples.
MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.
citing papers explorer
-
Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs
Jailbreak vulnerability in MLLMs is language- and modality-dependent, producing rank reversals in model safety between English and Spanish conditions.