Tag
This paper addresses the growing threat of pure-synthesis fake news videos generated by text-to-video models, introducing a new ternary classification task and the first pure-synthesis fake news video dataset (PS-FNVD), along with a Reasoning-guided framework (R-T2V) that achieves state-of-the-art detection accuracy.
This paper introduces FaceVid-Forensics-100K, a large-scale deepfake video dataset with fine-grained annotations, and proposes a multi-agent forensic reasoning framework (ARGUS) that uses four specialized expert agents and a judge agent to outperform closed-source models on deepfake detection.
Proposes using remote photoplethysmography (rPPG) waveforms to detect talking-face deepfakes, achieving AUC of 0.806 on the Celeb-DF++ TF subset, competitive with the best general-purpose detectors.
Halo by Scam AI is a product that helps users verify the authenticity of people on video calls, aiming to detect scams and deepfakes in real time. It was announced and linked via Product Hunt.
This paper proposes a linguistic-invariant spoofing detection framework that uses teacher-student adversarial learning and a variational information bottleneck to mitigate linguistic bias, achieving up to a 36.2% relative reduction in equal error rate across nine datasets.
An investigation by The Guardian reveals that brands are increasingly using AI-generated influencers on social media to promote products without disclosing their artificial nature, prompting calls for greater transparency and regulation.
Introduces Face-Fairness (FF), a plug-and-play framework for bias mitigation in deepfake detection, featuring Face-Feature Tuning (FFT) as the first demographic label-free fairness method that improves group accuracy and reduces performance gaps across demographics.
This discussion examines whether liveness detection models trained on historical deepfake samples can generalize to new synthetic media generation techniques, questioning the update cycle for vendors claiming deepfake detection capabilities.
Google is expanding SynthID and C2PA Content Credentials verification into Chrome and Search, while OpenAI embeds SynthID into images generated by its tools, marking a major push to make AI-generated content easier to detect online.
This paper proposes Emo-Boost, a multimodal deepfake detection framework that leverages emotion cues (audio-visual emotion recognition) as high-level semantic signals to improve generalization to unseen manipulation types, achieving a 2.1% average AUC improvement on the FakeAVCeleb dataset.
YouTube is expanding its AI likeness detection tool to all users aged 18 and older, enabling anyone to monitor for deepfakes of their face and request removal through YouTube's privacy policy.
This paper introduces the Alpha Blending Hypothesis, suggesting deepfake detectors primarily identify compositing artifacts rather than semantic anomalies. It proposes a method called BlenD that achieves superior cross-dataset generalization using real-only image augmentation with self-blended images.
A local distribution-aware detection framework that amplifies micro-scale statistical irregularities to identify AI-generated images with improved accuracy, outperforming baseline detectors across benchmarks.
Doppel launches an AI defense system powered by OpenAI's GPT-5 and o4-mini models that autonomously detects and stops deepfakes and online impersonation attacks at scale, reducing analyst workload by 80% and response times from hours to minutes.