activity
20182026
most citedHiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations

22 citations · 57 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

31 papers · 1 filter

cs.CV2026

Generalizable Face Forgery Detection via Separable Prompt Learning

Enrui Yang, Baoyuan Wu, Yuezun Li

Detecting face forgeries using CLIP has recently emerged as a promising direction. However, most existing methods focus on adapting its visual encoder, leaving the potential of the…

cs.CV2026

Detecting Diffusion-generated Images via Dynamic Assembly Forests

Mengxin Fu, Yuezun Li

Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transfor…

cs.CV2026

Off-the-shelf Vision Models Benefit Image Manipulation Localization

Zhengxuan Zhang, Keji Song, Junmin Hu +2

Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-spe…

cs.CV2025

Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics

Yuezun Li, Delong Zhu, Xinjie Cui +1

The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \textit{generalizable fore…

cs.CV2024

Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection

Delong Zhu, Yuezun Li, Baoyuan Wu +3

Face-swapping DeepFakes have become an escalating societal concern, attracting increasing attention in recent years. To counter this, we investigate a new proactive defense framewo…

cs.CV2024

Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection

Xinjie Cui, Yuezun Li, Delong Zhu +3

We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting…