← Back to all news
arXiv AI By Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana, Adnan Mahmood, Wei Bao, Kanchana Thilakarathna, Teng Joon Lim

FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation

Read the original on arXiv AI →

FedVideoMAE is a federated learning framework for short‑form video moderation that keeps raw videos on the device and uses a frozen VideoMAE backbone with lightweight LoRA and prompt parameters. Each training round performs self‑supervised masked video reconstruction while applying client‑side differential privacy and pairwise masked aggregation of adapter updates, keeping violence labels out of the federation. On the RWF‑2000 dataset, the method reduces the model‑state payload by 28.3× and achieves 77.25% accuracy without privacy mechanisms, dropping to 65.25–66.00% under differential privacy and secure aggregation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Aug 31

Can Tainted Pixels Expose Deepfake Videos?

The paper introduces TaintedPixels, a proactive video‑protection technique that embeds subtle, structured perturbations into the blue channel of facial regions. These perturbations remain invisible in the original video but become noticeable after black‑box manipulation, thereby flagging deepfakes. Experiments on three off‑the‑shelf manipulation tools and two detectors show that TaintedPixels achieves the highest forgery detection rate while keeping visual distortion minimal (LPIPS = 0.0042), and a human study confirms that protected videos are rarely suspected, whereas forgeries from protected sources are identified as fake far more often than those from unprotected sources.

By Juan Hu, Shaojing Fan, Sanjay Saha, Marc Herrera, Terence Sim
robotics
More like this →
arXiv Computer Vision
Aug 24

Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming

arXiv:2608.11645v2 Announce Type: replace Abstract: Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame...

By Hossein Khalili (UCLA), Philip Do (UCLA), Alexander Vilesov (UCLA), Achuta Kadambi (UCLA), Kittipat Apicharttrisorn (Nokia Bell Labs), Nader Sehatbakhsh (UCLA)
computer-visionsafety
More like this →
arXiv AI
Aug 26

STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning

The paper introduces STAIN-FL, a stealthy backdoor attack framework for federated video anomaly detection that uses natural surveillance conditions—such as low light, indoor settings, and crowd density—as contextual triggers. STAIN-FL manipulates anomaly labels and masks gradients to keep clean accuracy low while inducing trigger‑conditioned misclassification. Experiments on UCF‑Crime with I3D features show that sparse attacks remain undetectable, drop clean accuracy by less than 2%, yet achieve over 50% backdoor accuracy for hundreds of rounds under FedAvg and FedProx.

By Ashlinder Kaur, Purnima Murali Mohan, Zengxiang Li, Tram Truong-Huu
robotics
More like this →
arXiv Machine Learning
Jul 16

Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization

arXiv:2607. 13336v1 Announce Type: cross Abstract: Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which fine-tune a video diffusion model, and reference-based pipelines such as image-to-video generation.

By Yuxin Huang, Ziming Hong, Mingming Gong, Wanyu Wang, Jing Zhang, Tongliang Liu
diffusionfine-tuningsafety
More like this →