ShieldGemma 2: Robust and Tractable Image Content Moderation

We introduce ShieldGemma 2, a 4B parameter image content moderation model built on Gemma 3. This model provides robust safety risk predictions across the following key harm categories: Sexually Explicit, Violence \& Gore, and Dangerous Content for synthetic images (e.g. output of any image generation model) and natural images (e.g. any image input to a Vision-Language Model). We evaluated on both internal and external benchmarks to demonstrate state-of-the-art performance compared to LlavaGuard \citep{helff2024llavaguard}, GPT-4o mini \citep{hurst2024gpt}, and the base Gemma 3 model \citep{gemma_2025} based on our policies. Additionally, we present a novel adversarial data generation pipeline which enables a controlled, diverse, and robust image generation. ShieldGemma 2 provides an open image moderation tool to advance multimodal safety and responsible AI development.

FSD: An Initial Chinese Dataset for Fake Song Detection

Singing voice synthesis and singing voice conversion have significantly advanced, revolutionizing musical experiences. However, the rise of "Deepfake Songs" generated by these technologies raises concerns about authenticity. Unlike Audio DeepFake Detection (ADD), the field of song deepfake detection lacks specialized datasets or methods for song authenticity verification. In this paper, we initially construct a Chinese Fake Song Detection (FSD) dataset to investigate the field of song deepfake detection. The fake songs in the FSD dataset are generated by five state-of-the-art singing voice synthesis and singing voice conversion methods. Our initial experiments on FSD revealed the ineffectiveness of existing speech-trained ADD models for the task of song deepFake detection. Thus, we employ the FSD dataset for the training of ADD models. We subsequently evaluate these models under two scenarios: one with the original songs and another with separated vocal tracks. Experiment results show that song-trained ADD models exhibit a 38.58% reduction in average equal error rate compared to speech-trained ADD models on the FSD test set.