Safety Snowball Agent is an agent-based framework for evaluating how safe visual inputs can combine into unsafe behavior in large vision-language models. The framework accompanies the NeurIPS 2025 paper “Safe + Safe = Unsafe?” and probes a multimodal jailbreak mechanism that differs from traditional adversarial-image attacks.
Dec 2, 2025
NeurIPS 2025 work showing how safe images can combine into multimodal jailbreaks through the Safety Snowball effect.
Dec 2, 2025
Revealing and analyzing text bias in Large Audio-Language Models when audio and text inputs disagree.
Nov 1, 2025