Exposing and Mitigating Temporal Attack in Deepfake Video Detection
Peking University（北京大学）；New York University（纽约大学）；Huzhou University（湖州大学）；Institute of Science Tokyo（东京科学研究院）；Guangdong Institute of Intelligence Science and Technology（广东省智能科学与技术研究院）
While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum cues, rather than learning robust semantic causality. To mitigate this vulnerability, we propose SpInShield, a temporal spectral-invariant defense framework explicitly designed to decouple semantic motion from manipulatable spectral artifacts. We propose a learnable spectral adversary that dynamically synthesizes severe spectral deformations, simulating extreme attack scenarios. By employing a shortcut suppression optimization strategy, SpInShield compels the encoder to extract reliable forensic cues while purging unstable spectral statistics from the latent space. Experiments show that SpInShield obtains competitive performance on widely used datasets and outperforms the strongest baseline by 21.30 percentage points in AUC under simulated amplitude spectral attacks.
FakeChain: Exposing Shallow Cues in Multi-Step Deepfake Detection
Sungkyunkwan University Department of Artificial Intelligence Suwon Gyeonggi-do South Korea；Sungkyunkwan University Computer Science \& Engineering Department Suwon Gyeonggi-do South Korea；Sungkyunkwan University
Hunan University（湖南大学）；Nanjing University of Information Science and Technology（南京信息工程大学）
Residual-domain feature is very useful for Deepfake detection because it suppresses irrelevant content features and preserves key manipulation traces. However, inappropriate residual prediction will bring side effects on detection accuracy. In addition, residual-domain features are easily affected by image operations such as compression. Most existing works exploit either spatial-domain features or residual-domain features, while neglecting that two types of features are mutually correlated. In this paper, we propose a guided residuals network, namely GRnet, which fuses spatial-domain and resi…
With the rapid development of generation model, AI-based face manipulation technology, which called DeepFakes, has become more and more realistic. This means of face forgery can attack any target, which poses a new threat to personal privacy and property security. Moreover, the misuse of synthetic video shows potential dangers in many areas, such as identity harassment, pornography and news rumors. Inspired by the fact that the spatial coherence and temporal consistency of physiological signal are destroyed in the generated content, we attempt to find inconsistent patterns that can distinguish…
HOLA: Enhancing Audio-visual Deepfake Detection via Hierarchical Contextual Aggregations and Efficient Pre-training
Xi'an Jiaotong University（西安交通大学）；Zhengzhou University（郑州大学）；University of Science and Technology of China（中国科学技术大学）；Dalian University of Technology（大连理工大学）；Zhejiang Lab（浙江实验室）
Redundant Semantic Environment Filling via Misleading-Learning for Fair Deepfake Detection
School of Software, Nanchang University（南昌大学软件学院）；Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security, Shenzhen University（广东省智能信息处理重点实验室和深圳媒体安全重点实验室，深圳大学）；Department of Computer and Information Technology, Purdue University（计算机与信息科技系，普渡大学）；Guangdong Laboratory of Machine Perception and Intelligent Computing, Faculty of Engineering, Shenzhen MSU-BIT University（广东机器感知与智能计算实验室，工程学院，深圳MSU-BIT大学）
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors. Motivated by the fact that remote visual photoplethysmography (PPG) is made possible by monitoring the minuscule periodic changes of skin color due to blood pumping through the face, we conjecture that normal heartbeat rhythms found in the real face videos will be disrupted or even entirely broken in a DeepFake video, making it a potentially powerful indicator for DeepFake detection. …
DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis
Sun Yat-sen University（中山大学）；Pengcheng Laboratory（鹏城实验室）；Guilin University of Electronic Technology（桂林电子科技大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）
DeepAgent: A Dual Stream Multi Agent Fusion for Robust Multimodal Deepfake Detection
Applied Artificial Intelligence and Intelligent Systems (AAIINS) Laboratory（应用人工智能与智能系统实验室）；Department of Computer Science and Engineering（计算机科学与工程系）；University of Scholars（学者大学）；Faculty of Science and Information Technology（科学与信息技术学院）；Faculty of Science and Technology（科学与技术学院）
University at Albany, State University of New York（纽约州立大学奥尔巴尼分校）
In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as {\em DeepFake} videos hereafter) from real videos. Our method is based on the observations that current DeepFake algorithm can only generate images of limited resolutions, which need to be further warped to match the original faces in the source video. Such transforms leave distinctive artifacts in the resulting DeepFake videos, and we show that they can be effectively captured by convolutional neural networks (CNNs). Compared to previous methods which use a larg…
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection
The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））；University at Buffalo, State University of New York（纽约州立大学布法罗分校）；Nanjing University of Information Science and Technology（南京信息工程大学）
FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units
School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机科学学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））
FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection
Shenzhen University（深圳大学）；Shandong Artificial Intelligence Institute（山东省人工智能研究院）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Tianjin University of Technology（天津理工大学）
Advances in Artificial Intelligence and Image Processing are changing the way people interacts with digital images and video. Widespread mobile apps like FACEAPP make use of the most advanced Generative Adversarial Networks (GAN) to produce extreme transformations on human face photos such gender swap, aging, etc. The results are utterly realistic and extremely easy to be exploited even for non-experienced users. This kind of media object took the name of Deepfake and raised a new challenge in the multimedia forensics field: the Deepfake detection challenge. Indeed, discriminating a Deepfake f…
LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Electric Power Research Institute, China Southern Power Grid Company Ltd.（中国南方电网有限责任公司电力科学研究院）
The Partnership on AI（人工智能合作组织）；XPRIZE Foundation（XPRIZE基金会）；Syntiant Corp（Syntiant公司）；Thoughtful Technology Project（深思技术项目）
Synthetic media detection technologies label media as either synthetic or non-synthetic and are increasingly used by journalists, web platforms, and the general public to identify misinformation and other forms of problematic content. As both well-resourced organizations and the non-technical general public generate more sophisticated synthetic media, the capacity for purveyors of problematic content to adapt induces a \newterm{detection dilemma}: as detection practices become more accessible, they become more easily circumvented. This paper describes how a multistakeholder cohort from academi…
Deepfake poses a serious threat to the reliability of judicial evidence and intellectual property protection. In spite of an urgent need for Deepfake identification, existing pixel-level detection methods are increasingly unable to resist the growing realism of fake videos and lack generalization. In this paper, we propose a scheme to expose Deepfake through faint signals hidden in face videos. This scheme extracts two types of minute information hidden between face pixels-photoplethysmography (PPG) features and auto-regressive (AR) features, which are used as the basis for forensics in the te…
The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos. In this work, we describe a new method to expose fake face videos generated with neural networks. Our method is based on detection of eye blinking in the videos, which is a physiological signal that is not well presented in the synthesized fake videos. Our method is tested over benchmarks of eye-blinking detection datasets and also show promising performance on detecting videos generated with DeepFake.
Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（人工智能研究院）；University of Maryland（马里兰大学）；Chung-Ang University（Chung-Ang 大学）；Georgetown University（乔治城大学）；Miraflow AI
DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation
College of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；School of Electronics and Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）；School of Creative Technologies, Faculty of Creative and Cultural Industries, University of Portsmouth（朴茨茅斯大学创意与文化产业学院创意技术学院）；School of Computing and Mathematic Sciences, University of Leicester（莱斯特大学计算与数学科学学院）
Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification
Centre for Intelligent Machines, McGill University, Montreal, Canada（智能机器中心，麦吉尔大学，加拿大）；Mila -- Quebec AI Institute, Montreal, Canada（魁北克人工智能研究所）；Stanford University, Stanford, USA（斯坦福大学）；University of Copenhagen, Copenhagen, Denmark（哥本哈根大学）
Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval
University of Tübingen（图宾根大学）；Inria（法国国家信息与自动化研究所）；Ecole normale supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Recent deep learning based video synthesis approaches, in particular with applications that can forge identities such as "DeepFake", have raised great security concerns. Therefore, corresponding deep forensic methods are proposed to tackle this problem. However, existing methods are either based on unexplainable deep networks which greatly degrades the principal interpretability factor to media forensic, or rely on fragile image statistics such as noise pattern, which in real-world scenarios can be easily deteriorated by data compression. In this paper, we propose an fully-interpretable video …
Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
Nanjing University（南京大学）；China Mobile Information Technology Co., Ltd.（中国移动信息科技有限公司）；Nanjing University of Information Science and Technology（南京信息科技大学）
Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
Institute of Information Engineering, Chinese Academy of Sciences（信息工程研究所，中国科学院）；School of Cyber Science and Technology, Beihang University（北京航空航天大学信息与科学学院）
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）；Sun Yat-sen University（中山大学）；South China University of Technology（华南理工大学）
Deep-learning-based technologies such as deepfakes ones have been attracting widespread attention in both society and academia, particularly ones used to synthesize forged face images. These automatic and professional-skill-free face manipulation technologies can be used to replace the face in an original image or video with any target object while maintaining the expression and demeanor. Since human faces are closely related to identity characteristics, maliciously disseminated identity manipulated videos could trigger a crisis of public trust in the media and could even have serious politica…
