6 papers
Do VLMs Share Safety Neurons Across Modalities?
Jiaxuan Li, Jiahao Zhang, Duc Minh Vo +3
Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content in text. While prior work chara…
Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks
Jia Chengyu, AprilPyone MaungMaung, Huy H. Nguyen +2
Recent advances in vision-language models (VLMs) trained on web-scale image-text pairs have enabled impressive zero-shot transfer across a diverse range of visual tasks. However, c…
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
Pride Kavumba, Koki Wataoka, Huy H. Nguyen +2
In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response…
A Controllable 3D Deepfake Generation Framework with Gaussian Splatting
Wending Liu, Siyun Liang, Huy H. Nguyen +1
We propose a novel 3D deepfake generation framework based on 3D Gaussian Splatting that enables realistic, identity-preserving face swapping and reenactment in a fully controllable…
Measuring Human Involvement in AI-Generated Text: A Case Study on Academic Writing
Yuchen Guo, Zhicheng Dou, Huy H. Nguyen +3
Content creation has dramatically progressed with the rapid advancement of large language models like ChatGPT and Claude. While this progress has greatly enhanced various aspects o…
Zero-Shot Warning Generation for Misinformative Multimodal Content
Giovanni Pio Delvecchio, Huy Hong Nguyen, Isao Echizen
The widespread prevalence of misinformation poses significant societal concerns. Out-of-context misinformation, where authentic images are paired with false text, is particularly d…