Fake videos represent an important misinformation threat. While existing forensic networks have demonstrated strong performance on image forgeries, recent results reported on the Adobe VideoSham dataset show that these networks fail to identify fake content in videos. In this paper, we propose a new network that is able to detect and localize a wide variety of video forgeries and manipulations. To overcome challenges that existing networks face when analyzing videos, our network utilizes both forensic embeddings to capture traces left by manipulation, context embeddings to exploit forensic traces' conditional dependencies upon local scene content, and spatial attention provided by a deep, transformer-based attention mechanism. We create several new video forgery datasets and use these, along with publicly available data, to experimentally evaluate our network's performance. These results show that our proposed network is able to identify a diverse set of video forgeries, including those not encountered during training. Furthermore, our results reinforce recent findings that image forensic networks largely fail to identify fake content in videos.

法医分析取决于从操纵图像识别隐藏迹线。由于它们无法处理功能衰减和依赖主导空间特征，传统的神经网络失败。在这项工作中，我们提出了一种新颖的门控语言注意力网络（GCA-NET），用于全球背景学习的非本地关注块。另外，我们利用所通用的注意机制结合密集的解码器网络，以引导在解码阶段期间的相关特征的流动，允许精确定位。所提出的注意力框架允许网络通过过滤粗糙度来专注于相关区域。此外，通过利用多尺度特征融合和有效的学习策略，GCA-Net可以更好地处理操纵区域的比例变化。我们表明，我们的方法在多个基准数据集中平均优于最先进的网络，平均为4.2％-5.4％AUC。最后，我们还开展了广泛的消融实验，以展示该方法对图像取证的鲁棒性。

Online media data, in the forms of images and videos, are becoming mainstream communication channels. However, recent advances in deep learning, particularly deep generative models, open the doors for producing perceptually convincing images and videos at a low cost, which not only poses a serious threat to the trustworthiness of digital information but also has severe societal implications. This motivates a growing interest of research in media tampering detection, i.e., using deep learning techniques to examine whether media data have been maliciously manipulated. Depending on the content of the targeted images, media forgery could be divided into image tampering and Deepfake techniques. The former typically moves or erases the visual elements in ordinary images, while the latter manipulates the expressions and even the identity of human faces. Accordingly, the means of defense include image tampering detection and Deepfake detection, which share a wide variety of properties. In this paper, we provide a comprehensive review of the current media tampering detection approaches, and discuss the challenges and trends in this field for future research.

In this paper we present TruFor, a forensic framework that can be applied to a large variety of image manipulation methods, from classic cheapfakes to more recent manipulations based on deep learning. We rely on the extraction of both high-level and low-level traces through a transformer-based fusion architecture that combines the RGB image and a learned noise-sensitive fingerprint. The latter learns to embed the artifacts related to the camera internal and external processing by training only on real data in a self-supervised manner. Forgeries are detected as deviations from the expected regular pattern that characterizes each pristine image. Looking for anomalies makes the approach able to robustly detect a variety of local manipulations, ensuring generalization. In addition to a pixel-level localization map and a whole-image integrity score, our approach outputs a reliability map that highlights areas where localization predictions may be error-prone. This is particularly important in forensic applications in order to reduce false alarms and allow for a large scale analysis. Extensive experiments on several datasets show that our method is able to reliably detect and localize both cheapfakes and deepfakes manipulations outperforming state-of-the-art works. Code will be publicly available at https://grip-unina.github.io/TruFor/

In this paper, we introduce MINTIME, a video deepfake detection approach that captures spatial and temporal anomalies and handles instances of multiple people in the same video and variations in face sizes. Previous approaches disregard such information either by using simple a-posteriori aggregation schemes, i.e., average or max operation, or using only one identity for the inference, i.e., the largest one. On the contrary, the proposed approach builds on a Spatio-Temporal TimeSformer combined with a Convolutional Neural Network backbone to capture spatio-temporal anomalies from the face sequences of multiple identities depicted in a video. This is achieved through an Identity-aware Attention mechanism that attends to each face sequence independently based on a masking operation and facilitates video-level aggregation. In addition, two novel embeddings are employed: (i) the Temporal Coherent Positional Embedding that encodes each face sequence's temporal information and (ii) the Size Embedding that encodes the size of the faces as a ratio to the video frame size. These extensions allow our system to adapt particularly well in the wild by learning how to aggregate information of multiple identities, which is usually disregarded by other methods in the literature. It achieves state-of-the-art results on the ForgeryNet dataset with an improvement of up to 14% AUC in videos containing multiple people and demonstrates ample generalization capabilities in cross-forgery and cross-dataset settings. The code is publicly available at https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection.

Figure 1: FaceForensics++ is a dataset of facial forgeries that enables researchers to train deep-learning-based approaches in a supervised fashion. The dataset contains manipulations created with four state-of-the-art methods, namely, Face2Face, FaceSwap, DeepFakes, and NeuralTextures.

近年来，视觉伪造达到了人类无法识别欺诈的复杂程度，这对信息安全构成了重大威胁。出现了广泛的恶意申请，例如名人的假新闻，诽谤或勒索，政治战中的政治家冒充，以及谣言的传播吸引观点。结果，已经提出了一种富有的视觉验证技术，以试图阻止这种危险的趋势。在本文中，我们使用全面的和经验方法，提供了一种基准，可以对视觉伪造和视觉取证进行深入的洞察。更具体地，我们开发一个独立的框架，整合最先进的假冒生成器和探测器，并使用各种标准来测量这些技术的性能。我们还对基准测试结果进行了详尽的分析，确定了在措施与对策之间永无止境的战争中的比较参考的方法的特征。

深度学习已成功地用于解决从大数据分析到计算机视觉和人级控制的各种复杂问题。但是，还采用了深度学习进步来创建可能构成隐私，民主和国家安全威胁的软件。最近出现的那些深度学习驱动的应用程序之一是Deepfake。 DeepFake算法可以创建人类无法将它们与真实图像区分开的假图像和视频。因此，可以自动检测和评估数字视觉媒体完整性的技术的建议是必不可少的。本文介绍了一项用于创造深击的算法的调查，更重要的是，提出的方法旨在检测迄今为止文献中的深击。我们对与Deepfake技术有关的挑战，研究趋势和方向进行了广泛的讨论。通过回顾深层味和最先进的深层检测方法的背景，本研究提供了深入的深层技术的概述，并促进了新的，更强大的方法的发展，以应对日益挑战性的深击。

为了防止操纵图像内容（例如剪接，复制移动和删除），我们开发了一个渐进的时空通道相关网络（PSCC-NET），以检测和本地化图像操作。 PSCC-NET以两路程的过程处理图像：一条自上而下的路径，该路径提取本地和全局特征以及检测输入图像是否被操纵的自下而上的路径，并在多个尺度上估算其操纵掩码，每个尺度都在其中面具的条件是在前一个。与传统的编码器编码器和无流动结构不同，PSCC-NET在不同尺度上的功能具有密集的交叉连接，以粗到更细致的方式产生操纵罩。此外，空间通道相关模块（SCCM）捕获自下而上路径中的空间和渠道相关性，该路径赋予了整体提示，使网络能够应对广泛的操纵攻击。得益于轻巧的主链和渐进式机制，PSCC-NET可以在50+ fps下处理1,080p图像。广泛的实验证明了PSCC-NET优于最先进方法在检测和定位方面。

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.

基于高质量标签的鱼类跟踪和细分的DNN很昂贵。替代无监督的方法取决于视频数据中自然发生的空间和时间变化来生成嘈杂的伪界图标签。这些伪标签用于训练多任务深神经网络。在本文中，我们提出了一个三阶段的框架，用于强大的鱼类跟踪和分割，其中第一阶段是光流模型，该模型使用帧之间的空间和时间一致性生成伪标签。在第二阶段，一个自我监督的模型会逐步完善伪标签。在第三阶段，精制标签用于训练分割网络。在培训或推理期间没有使用人类注释。进行了广泛的实验来验证我们在三个公共水下视频数据集中的方法，并证明它对视频注释和细分非常有效。我们还评估框架对不同成像条件的鲁棒性，并讨论当前实施的局限性。

Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific biometric characteristics that a synthetic generator cannot likely reproduce. Accordingly, we extract high-level audio-visual biometric features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the moving-face and audio segment embeddings that are most discriminative for each identity. As a result, when the video and/or audio of a person is manipulated, its representation in the embedding space becomes inconsistent with the real identity, allowing reliable detection. Training is carried out exclusively on real talking-face videos, thus the detector does not depend on any specific manipulation method and yields the highest generalization ability. In addition, our method can detect both single-modality (audio-only, video-only) and multi-modality (audio-video) attacks, and is robust to low-quality or corrupted videos by building only on high-level semantic features. Experiments on a wide variety of datasets confirm that our method ensures a SOTA performance, with an average improvement in terms of AUC of around 3%, 10%, and 4% for high-quality, low quality, and attacked videos, respectively. https://github.com/grip-unina/poi-forensics

面部伪造技术的最新进展几乎可以产生视觉上无法追踪的深冰录视频，这些视频可以通过恶意意图来利用。结果，研究人员致力于深泡检测。先前的研究已经确定了局部低级提示和时间信息在追求跨层次方法中概括的重要性，但是，它们仍然遭受鲁棒性问题的影响。在这项工作中，我们提出了基于本地和时间感知的变压器的DeepFake检测（LTTD）框架，该框架采用了局部到全球学习协议，特别关注本地序列中有价值的时间信息。具体而言，我们提出了一个局部序列变压器（LST），该局部序列变压器（LST）对限制空间区域的序列进行了时间一致性，其中低级信息通过学习的3D滤波器的浅层层增强。基于局部时间嵌入，我们然后以全球对比的方式实现最终分类。对流行数据集进行的广泛实验验证了我们的方法有效地发现了本地伪造线索并实现最先进的表现。

在过去的几年中，虚假内容的增长速度令人难以置信。社交媒体和在线平台的传播使他们的恶意演员越来越多地传播大规模的传播。同时，由于虚假图像生成方法的扩散越来越大，已经提出了许多基于深度学习的检测技术。这些方法中的大多数依赖于从RGB图像中提取显着特征，以通过二进制分类器检测图像是假的或真实的。在本文中，我们提出了DepthFake，这是一项有关如何使用深度图改善基于经典RGB的方法的研究。深度信息是从具有最新单眼深度估计技术的RGB图像中提取的。在这里，我们证明了深度映射对深料检测任务的有效贡献对稳健的预训练架构。实际上，针对faceforensic ++数据集的标准RGB体系结构，对于一些DeepFake攻击，对一些DeepFake攻击的平均提高了3.20％和11.7％。

作为内容编辑成熟的工具，以及基于人工智能（AI）综合媒体增长的算法，在线媒体上的操纵内容的存在正在增加。这种现象导致错误信息的传播，从而更需要区分“真实”和“操纵”内容。为此，我们介绍了Videosham，该数据集由826个视频（413个真实和413个操纵）组成。许多现有的DeepFake数据集专注于两种类型的面部操作 - 与另一个受试者的面部交换或更改现有面部。另一方面，Videosham包含更多样化的，上下文丰富的和以人为本的高分辨率视频，使用6种不同的空间和时间攻击组合来操纵。我们的分析表明，最新的操纵检测算法仅适用于一些特定的攻击，并且在Videosham上不能很好地扩展。我们在亚马逊机械土耳其人上进行了一项用户研究，其中1200名参与者可以区分Videosham中的真实视频和操纵视频。最后，我们更深入地研究了人类和sota-Algorithms表演的优势和劣势，以识别需要用更好的AI算法填补的差距。

DeepFake是指量身定制和合成生成的视频，这些视频现在普遍存在并大规模传播，威胁到在线可用信息的可信度。尽管现有的数据集包含不同类型的深击，但它们的生成技术各不相同，但它们并不考虑以“系统发育”方式进展。现有的深层面孔可能与另一个脸交换。可以多次执行面部交换过程，并且可以演变出最终的深层效果，以使DeepFake检测算法混淆。此外，许多数据库不提供应用的生成模型作为目标标签。模型归因通过提供有关所使用的生成模型的信息，有助于增强检测结果的解释性。为了使研究界能够解决这些问题，本文提出了Deephy，这是一种新型的DeepFake系统发育数据集，由使用三种不同的一代技术生成的5040个DeepFake视频组成。有840个曾经交换深击的视频，2520个换两次交换深击的视频和1680个换装深击的视频。使用超过30 GB的大小，使用1,352 GB累积内存的18 GPU在1100多个小时内准备了数据库。我们还使用六种DeepFake检测算法在Deephy数据集上展示了基准。结果突出了需要发展深击模型归因的研究，并将过程推广到各种深层生成技术上。该数据库可在以下网址获得：http：//iab-rubric.org/deephy-database

随着面部伪造技术的快速发展，DeepFake视频在数字媒体上引起了广泛的关注。肇事者大量利用这些视频来传播虚假信息并发表误导性陈述。大多数现有的DeepFake检测方法主要集中于纹理特征，纹理特征可能会受到外部波动（例如照明和噪声）的影响。此外，基于面部地标的检测方法对外部变量更强大，但缺乏足够的细节。因此，如何在空间，时间和频域中有效地挖掘独特的特征，并将其与面部地标融合以进行伪造视频检测仍然是一个悬而未决的问题。为此，我们提出了一个基于多种模式的信息和面部地标的几何特征，提出了地标增强的多模式图神经网络（LEM-GNN）。具体而言，在框架级别上，我们设计了一种融合机制来挖掘空间和频域元素的联合表示，同时引入几何面部特征以增强模型的鲁棒性。在视频级别，我们首先将视频中的每个帧视为图中的节点，然后将时间信息编码到图表的边缘。然后，通过应用图形神经网络（GNN）的消息传递机制，将有效合并多模式特征，以获得视频伪造的全面表示。广泛的实验表明，我们的方法始终优于广泛使用的基准上的最先进（SOTA）。

动态对象对机器人对环境的看法产生了重大影响，这降低了本地化和映射等基本任务的性能。在这项工作中，我们通过在由动态对象封闭的区域中合成合理的颜色，纹理和几何形状来解决这个问题。我们提出了一种新的几何感知Dynafill架构，其遵循粗略拓扑，并将我们所通用的经常性反馈机制结合到自适应地融合来自之前的时间步来的信息。我们使用对抗性培训来优化架构，以综合精细的现实纹理，使其能够以空间和时间相干的方式在线在线遮挡地区的幻觉和深度结构，而不依赖于未来的帧信息。将我们的待遇问题作为图像到图像到图像的翻译任务，我们的模型还纠正了与场景中动态对象的存在相关的区域，例如阴影或反射。我们引入了具有RGB-D图像，语义分段标签，摄像机的大型高估数据集，以及遮挡区域的地面RGB-D信息。广泛的定量和定性评估表明，即使在挑战天气条件下，我们的方法也能实现最先进的性能。此外，我们使用综合图像显示基于检索的视觉本地化的结果，该图像证明了我们方法的效用。

玻璃在我们的日常生活中非常普遍。现有的计算机视觉系统忽略了它，因此可能会产生严重的后果，例如，机器人可能会坠入玻璃墙。但是，感知玻璃的存在并不简单。关键的挑战是，任意物体/场景可以出现在玻璃后面。在本文中，我们提出了一个重要的问题，即从单个RGB图像中检测玻璃表面。为了解决这个问题，我们构建了第一个大规模玻璃检测数据集（GDD），并提出了一个名为GDNet-B的新颖玻璃检测网络，该网络通过新颖的大型场探索大型视野中的丰富上下文提示上下文特征集成（LCFI）模块并将高级和低级边界特征与边界特征增强（BFE）模块集成在一起。广泛的实验表明，我们的GDNET-B可以在GDD测试集内外的图像上达到满足玻璃检测结果。我们通过将其应用于其他视觉任务（包括镜像分割和显着对象检测）来进一步验证我们提出的GDNET-B的有效性和概括能力。最后，我们显示了玻璃检测的潜在应用，并讨论了可能的未来研究方向。

With the rapid development of deep generative models (such as Generative Adversarial Networks and Auto-encoders), AI-synthesized images of the human face are now of such high quality that humans can hardly distinguish them from pristine ones. Although existing detection methods have shown high performance in specific evaluation settings, e.g., on images from seen models or on images without real-world post-processings, they tend to suffer serious performance degradation in real-world scenarios where testing images can be generated by more powerful generation models or combined with various post-processing operations. To address this issue, we propose a Global and Local Feature Fusion (GLFF) to learn rich and discriminative representations by combining multi-scale global features from the whole image with refined local features from informative patches for face forgery detection. GLFF fuses information from two branches: the global branch to extract multi-scale semantic features and the local branch to select informative patches for detailed local artifacts extraction. Due to the lack of a face forgery dataset simulating real-world applications for evaluation, we further create a challenging face forgery dataset, named DeepFakeFaceForensics (DF^3), which contains 6 state-of-the-art generation models and a variety of post-processing techniques to approach the real-world scenarios. Experimental results demonstrate the superiority of our method to the state-of-the-art methods on the proposed DF^3 dataset and three other open-source datasets.