Video Inter-Frame Forgery Identification Based on Consistency of Correlation Coefficients of Gray Values

Identifying inter-frame forgery is a hot topic in video forensics. In this paper, we propose a method based on the assumption that the correlation coefficients of gray values is consistent in an original video, while in forgeries the consistency will be destroyed. We first extract the consistency of correlation coefficients of gray values (CCCoGV for short) after normalization and quantization as distinguishing feature to identify interframe forgeries. Then we test the CCCoGV in a large database with the help of SVM (Support Vector Machine). Experimental results show that the proposed method is efficient in classifying original videos and forgeries. Furthermore, the proposed method performs also pretty well in classifying frame insertion and frame deletion forgeries.

Copy-Move Forgeries Detection and Localization Using Two Levels of Keypoints Extraction

Copy-move offense is considerably used to conceal or hide several data in the digital image for specific aim, and onto this offense some portion of the genuine image is reduplicated and pasted in the same image. Therefore, Copy-Move forgery is a very significant problem and active research area to check the confirmation of the image. In this paper, a system for Copy Move Forgery detection is proposed. The proposed system is composed of two stages: one is called the detection stages and the second is called the refine detection stage. The detection stage is executed using Speeded-Up Robust Feature (SURF) and Binary Robust Invariant Scalable Keypoints (BRISK) for feature detection and in the refine detection stage, image registration using non-linear transformation is used to enhance detection efficiency. Initially, the genuine image is picked, and then both SURF and BRISK feature extractions are used in parallel to detect the interest keypoints. This gives an appropriate number of interest points and gives the assurance for finding the majority of the manipulated regions. RANSAC is employed to find the superior group of matches to differentiate the manipulated parts. Then, non-linear transformation between the best-matched sets from both extraction features is used as an optimization to get the best-matched set and detect the copied regions. A number of numerical experiments performed using many benchmark datasets such as, the CASIA v2.0, MICC-220, MICC-F600 and MICC-F2000 datasets. With the proposed algorithm, an overall average detection accuracy of 95.33% is obtained for evaluation carried out with the aforementioned databases. Forgery detection achieved True Positive Rate of 97.4% for tampered images with object translation, different degree of rotation and enlargement. Thus, results from different datasets have been set, proving that the proposed algorithm can individuate the altered areas, with high reliability and dealing with multiple cloning.

An analysis of silver candlesticks from a casting point of view:originals,copies,forgeries

Collecting silver artefacts has traditionally been a very popular hobby.Silver is addictive,therefore the number of potential collectors and investors appears to grow each year.Unfortunately,increases in the interest and buying potentials resulted in a number of forgeries manufactured and introduced to the open antique market.The items such as early silver candlesticks dictate a very high price,for many high quality fakes show very good appearances and matching similarities with originals.Such copies are traditionally manufactured by casting using the original items as patterns.Small details and variances in design features,position and shape of hallmarks,including the final surface quality are usual features to distinguish the fakes from the originals.This paper presents results of a study conducted on several silver candlesticks,including two artefacts bearing features of those produced in the mid 18th century,one original Italian candelabrum from Fascist era,and small candlesticks made in the early 20th century.Also,the paper presents some interesting contemporary coins-replicas of many those produced in different countries.The coins were offered for sale by unscrupulous dealers via auctions and e-bays.Finally the main results and findings from this study are discussed from a manufacturing point of view,such as fabrication technology,surface quality and hallmarks,which will help the collectors,dealers and investors to detect and avoid forgeries.

说话人音频攻击与对抗技术研究综述

文中概括了说话人音频攻击与对抗技术的最新进展。由于说话人音频攻击已经成为语音应用安全的严重威胁,以WaveNet、Transformer和GAN三种模型在音频攻击技术中的应用作为节点,分别介绍以其为基础的音频攻击技术。音频对抗技术则以涵盖的攻击技术分为3类,分别是基础音频攻击、重放攻击和深度伪造攻击。系统地阐述了音频攻击与对抗技术的最新研究成果,并分析比较了各算法在不同条件下的优劣,同时还介绍了音频技术常用的数据集。最后结合该领域目前的研究现状,提出了说话人音频攻防对抗技术研究中亟待关注与研究的问题。

基于多尺度时空特征和篡改概率改善换脸检测的跨库性能

目前大多DeepFake换脸检测算法过于依赖局部特征,尽管库内检测性能尚佳,但容易出现过拟合,导致跨库检测性能不理想,即泛化性能不够好。有鉴于此,文中提出一种基于多尺度时空特征和篡改概率的换脸视频检测算法,目的是利用假脸视频中广泛存在的帧间时域不连续性缺陷来解决现有检测算法在跨库、跨伪造方式和视频压缩时性能明显下降的问题,改善泛化检测能力。该算法包括3个模块:为检测假脸视频在时域上留下的不连续痕迹,设计了一个多尺度时空特征提取模块;为自适应计算多尺度时空特征之间的时空域关联性,设计了一个三维双注意力机制模块;为预测随机选取的像素点的篡改概率和构造监督掩膜,设计了一个辅助监督模块。将所提出的算法在FF++、DFD、DFDC、CDF等公开大型标准数据库中进行实验,并与基线算法和近期发布的同类算法进行对比。结果显示:文中算法在保持库内平均检测性能优良的同时,跨库检测和抗视频压缩时的综合性能最好,跨伪造方法检测时的综合性能中等偏上。实验结果验证了文中算法的有效性。

书商的狡黠:《徐文长佚草》医学文献之谜发覆

自1926年慈溪沈德寿排印本《徐文长佚草》行世后,徐渭有医学著作的信息已然成为事实。然而,在徐渭的诗文中无为人治病及自行处方服药之记录,与其相关人员也未言及其能医。而比沈德寿排印本《徐文长佚草》更早的同名同卷本——清初息耕堂抄本《徐文长佚草》根本没有医学内容。沈德寿排印本《徐文长佚草》中的医学部分其实是明代医官方谷《医林绳墨》卷七、卷八中的内容。

“非羁码”的风险隐忧与前景展望

“非羁码”作为数字技术与检察监督的跨界融合产物,不仅助力实现数字赋能“云”上监管,还顺应了我国数字检察创新发展的要求,有力推动了新型法律监督数字化道路的建设。然而,在适用过程中,“非羁码”存在运行困境以及潜在风险,如:研发机关权力边界不明晰,对犯罪嫌疑人、被告人个人信息保护的法律规定缺位,诱发“数字伪造”“数字接管”,多元化、系统化的监管联合机制尚未建立等。作为一种新型监管手段,“非羁码”应着力降低自身风险隐患,助力维护人权保障与诉讼权利的有机平衡,以实现数字赋能法律监督的新跨越为目标。这具体包括:明确“非羁码”的功能定位与研发机关的权力边界;加强对数字人权的保障;打破思维定式,以“非羁码”使用者的立场为导向;厘清司法主体地位,坚守“技术服务于法治”的初衷;通过优化协作式监管方法,明确各机关之间的责任分工和数字平台建设及应用的职责,构建多元化联合机制,加强对犯罪嫌疑人、被告人的监管等方面的针对性措施,进一步建构和完善应对新时代数字化的监管体系,助力实现“加快建设网络强国、数字强国”的美好愿景。

今本《古文尚书·汤诰》非伪书新证

今本《古文尚书》的《汤诰》从南宋以来被学术界怀疑为所谓“伪古文尚书”之一。本文列举了十八条证据证明今本《汤诰》一定是商代的古本文献,不可能是魏晋人所能伪造的。本文将西汉以前引述《汤诰》的古文献和今本《汤诰》逐一予以精密的比对,论证了只能是春秋战国的文献引述今本《汤诰》,不可能是今本《汤诰》在那些文献的基础上创作而成。尤其是本文发现了今本《汤诰》的“惟皇上帝”一语可与西周金文精准对应,也与清华简精准对应,这是证明今本《汤诰》不伪的坚强证据。今本《汤诰》和《史记》所引《汤诰》是古本《汤诰》的上下篇,都是先秦的真实文献。先秦墨家所传的《尚书》文本和对《尚书》的阐释,与儒家的传本和阐释有所不同。儒家的《尚书》传本和阐释比墨家更可信。

多模态部分伪造数据集的构建与基准检测

针对现有视频伪造数据集缺少多模态伪造场景与部分伪造场景的问题,构建一个综合使用多种音、视频伪造方法的、伪造比例可调的多模态部分伪造数据集PartialFAVCeleb。所提数据集基于FakeAVCeleb多模态伪造数据集,并通过拼接真伪数据构建,其中伪造数据由FaceSwap、FSGAN(Face Swapping Generative Adversarial Network)、Wav2Lip(Wave to Lip)和SV2TTS(Speaker Verification to Text-To-Speech)这4种方法生成。在拼接过程中,使用概率方法生成伪造片段在时域与模态上的定位,并对边界进行随机化处理以贴合实际伪造场景,并通过素材筛选避免背景跳变现象。最终生成的数据集对于每个伪造比例可产生3970条视频数据。在基准检测中,使用多种音视频特征提取器,并分别进行强、弱监督两种条件下的测试,其中弱监督测试基于层次多示例学习(HMIL)方法实现。测试结果显示,各个测试模型在伪造比例较低数据上的性能表现显著低于在伪造比例较高数据上的性能,且弱监督条件下各模型的性能表现显著低于强监督条件下的表现,这验证了该部分伪造数据集的弱监督检测困难性。以上结果表明,以所提数据集为代表的多模态部分伪造场景有充分的研究价值。

基于深度学习的多特征融合人脸鉴伪模型

人脸伪造给网络安全带来了重大挑战。针对现有人脸鉴伪模型特征单一、准确率低的问题,提出了一种基于深度学习的多特征融合人脸鉴伪模型。该模型设计了不同特征提取模块,用以获取不同尺度的特征表示。并学习如何有效融合这些语义信息以准确判定是否伪造,从而显著提升模型的准确率和鲁棒性。最后在公开数据集FaceForensics++上进行大量实验验证。实验结果显示,与现有方法相比,设计的模型有明显的性能提升。

深度视频修复篡改的被动取证研究

深度视频修复技术就是利用深度学习技术,对视频中的缺失区域进行补全或移除特定目标对象。它也可用于合成篡改视频,其篡改后的视频很难通过肉眼辨别真假,尤其是一些恶意修复的视频在社交媒体上传播时,容易造成负面的社会舆论。目前,针对深度视频修复篡改的被动检测技术起步较晚,尽管它已经得到一些关注,但在研究的深度和广度上还远远不够。因此,本文提出一种基于级联Conv GRU和八方向局部注意力的被动取证技术,从时空域角度实现对深度修复篡改区域的定位检测。首先,为了提取修复区域的更多特征,RGB帧和错误级分析帧ELA平行输入编码器中,通过通道特征级融合,生成不同尺度的多模态特征。其次,在解码器部分,使用编码器生成的多尺度特征与串联的Conv GRU进行通道级融合来捕捉视频帧间的时域不连续性。最后,在编码器的最后一级RGB特征后,引入八方向局部注意力模块,该模块通过八个方向来关注像素的邻域信息,捕捉修复区域像素间的异常。实验中,本文使用了VI、OP、DSTT和FGVC四种最新的深度视频修复方法与已有的深度视频修复篡改检测方法HPF和VIDNet进行了对比,性能优于HPF且在编码器参数仅VIDNet的五分之一的情况下获得与VIDNet可比的性能。结果表明,本文所提方法利用多尺度双模态特征和引入的八方向局部注意力模块来关注像素间的相关性,使用Conv GRU捕捉时域异常,实现像素级的篡改区域定位,获得精准的定位效果。

抗高强度椒盐噪声的鲁棒拼接取证算法

在图像取证领域,图像拼接检测技术可以通过分析图像内容识别拼接,并定位拼接区域。然而,在传输、扫描等常见场景中,椒盐(s&p)噪声会不可避免地随机出现,且随着噪声强度的增加,当前拼接取证方法的效力将逐渐减弱,甚至失效,极大地影响了现有拼接取证方法的效果。因此,提出一种能够抵御高强度椒盐噪声的拼接取证算法。所提算法分为2个主要部分:预处理部分和拼接取证部分。首先,预处理部分利用ResNet32与中值滤波器的融合,去除图像中的椒盐噪声,并通过卷积层恢复受损的图像内容,从而最大限度地消除椒盐噪声对拼接取证部分的影响并恢复图像细节;其次,拼接取证部分基于暹罗网络结构,提取与图像唯一性相关的噪声伪影,并通过不一致判断识别拼接区域。在通用篡改数据集上的实验结果表明,所提算法在RGB图像和灰度图像上均取得了良好的效果。在10%噪声场景下与FS(Forensic Similarity)和PSCC-Net(Progressive Spatio-Channel Correlation Network)取证算法相比,所提算法将马修斯相关系数(MCC)值提升超过50%,这验证了所提算法在被噪声干扰的篡改图像上取证的有效性和先进性。

Image Splicing Forgery Detection Using Feature-Based of Sonine Functions and Deep Features

The growing prevalence of fake images on the Internet and social media makes image integrity verification a crucial research topic.One of the most popular methods for manipulating digital images is image splicing,which involves copying a specific area from one image and pasting it into another.Attempts were made to mitigate the effects of image splicing,which continues to be a significant research challenge.This study proposes a new splicing detectionmodel,combining Sonine functions-derived convex-based features and deep features.Two stages make up the proposed method.The first step entails feature extraction,then classification using the“support vector machine”(SVM)to differentiate authentic and spliced images.The proposed Sonine functions-based feature extraction model reveals the spliced texture details by extracting some clues about the probability of image pixels.The proposed model achieved an accuracy of 98.93% when tested with the CASIA V2.0 dataset“Chinese Academy of Sciences,Institute of Automation”which is a publicly available dataset for forgery classification.The experimental results show that,for image splicing forgery detection,the proposed Sonine functions-derived convex-based features and deep features outperform state-of-the-art techniques in terms of accuracy,precision,and recall.Overall,the obtained detection accuracy attests to the benefit of using the Sonine functions alongside deep feature representations.Finding the regions or locations where image tampering has taken place is limited by the study.Future research will need to look into advanced image analysis techniques that can offer a higher degree of accuracy in identifying and localizing tampering regions.

针对低质量视频的双支流人脸伪造检测方法

随着人脸伪造技术不断的发展,如今经过伪造后的视频和图片的人脸伪造质量大幅度提升,这对人身安全、财产安全乃至公共安全存在一定的危害性。因此,迫切需要一种有效的检测方法来区分真假人脸。然而,现有的检测方法面对低质量的虚假人脸视频时存在一定的局限性,即面对压缩过后的低质量视频检测性能较差,此外,泛化性能较差,检测准确率有所下降。为了提升检测网络的准确性和泛化性,将语义信息和噪声信息相结合,提出一个双支流网络,在关注图像语义信息的同时通过高频噪声信息展示出伪造区域和真实区域的不一致性。利用高频噪声信息暴露出的不一致性,重点关注图像语义信息中的伪造痕迹。交互模块增进语义信息和高频信息之间的交互性与融合性。在FaceForensics++数据集进行了训练和测试,并在Celeb-DF数据集上评估该模型的跨数据集泛化性能。从实验结果中可以证明该模型的有效性和可靠性。

基于帧内-帧间自融合的双流泛化人脸伪造检测方法

现有人脸伪造检测方法往往在已知伪造类型上表现良好,但面对未知数据时检测性能有所下降,模型易受到过拟合的影响,检测泛化性不足。针对此问题,提出一种基于帧内-帧间自融合的双流泛化人脸伪造检测方法,从数据增强和检测器改进2个方面提高检测泛化性。设计帧内-帧间自融合模块,分别利用同帧人脸、帧间人脸进行数据增强:帧内自融合子模块利用同帧人脸生成训练数据,从而避免人脸图像身份信息干扰;帧间自融合子模块利用伪造视频的帧间不一致性,进一步构造多样性丰富、逼真的训练数据集,从而有效防止模型的过拟合,确保检测模型的泛化能力。此外,设计基于通道注意力机制的双流特征融合网络,在网络的浅层提取RGB特征、高频特征并进行融合来挖掘伪造信息,在提升模型性能的同时缓解网络的参数增长。将模型在4个数据集上与9种主流检测方法进行对比实验,结果表明:在跨数据集实验中,所提方法较次优方法AUC均值提高1.52个百分点,EER均值降低1.5个百分点;在跨伪造方法实验中,所提方法在4种伪造方法子数据集上均取得最优或次优效果。实验结果验证了该方法优秀的泛化能力。

Electricity Carbon Quota Trading Scheme based on Certificateless Signature and Blockchain

The carbon tradingmarket can promote“carbon peaking”and“carbon neutrality”at low cost,but carbon emission quotas face attacks such as data forgery,tampering,counterfeiting,and replay in the electricity trading market.Certificateless signatures are a new cryptographic technology that can address traditional cryptography’s general essential certificate requirements and avoid the problem of crucial escrowbased on identity cryptography.However,most certificateless signatures still suffer fromvarious security flaws.We present a secure and efficient certificateless signing scheme by examining the security of existing certificateless signature schemes.To ensure the integrity and verifiability of electricity carbon quota trading,we propose an electricity carbon quota trading scheme based on a certificateless signature and blockchain.Our scheme utilizes certificateless signatures to ensure the validity and nonrepudiation of transactions and adopts blockchain technology to achieve immutability and traceability in electricity carbon quota transactions.In addition,validating electricity carbon quota transactions does not require time-consuming bilinear pairing operations.The results of the analysis indicate that our scheme meets existential unforgeability under adaptive selective message attacks,offers conditional identity privacy protection,resists replay attacks,and demonstrates high computing and communication performance.

Design & Test of an Advanced Web Security Analysis Tool (AWSAT)

Considering the escalating frequency and sophistication of cyber threats targeting web applications, this paper proposes the development of an automated web security analysis tool to address the accessibility gap for non-security professionals. This paper presents the design and implementation of an automated web security analysis tool, AWSAT, aimed at enabling individuals with limited security expertise to effectively assess and mitigate vulnerabilities in web applications. Leveraging advanced scanning techniques, the tool identifies common threats such as Cross-Site Scripting (XSS), SQL Injection, and Cross-Site Request Forgery (CSRF), providing detailed reports with actionable insights. By integrating sample payloads and reference study links, the tool facilitates informed decision-making in enhancing the security posture of web applications. Through its user-friendly interface and robust functionality, the tool aims to democratize web security practices, empowering a wider audience to proactively safeguard against cyber threats.

基于注意力机制的渐进式图像复制粘贴篡改检测

针对图像复制粘贴篡改检测深度学习方法中特征提取阶段信息丢失问题,本文提出基于注意力机制的渐进式图像复制粘贴篡改检测模型.该模型在特征提取阶段不同于先下采样得到强语义信息,再上采样恢复高分辨率恢复位置信息的常见结构,而是整个过程保持并行多分辨率,不同分辨率分支之间信息交互,同时达到强语义信息和精准位置信息的目的 .特征提取的关键是:首先给出不同分辨率特征图;然后结合空间与通道的注意力机制由低到高渐进式进行特征连接,生成对应分辨率下的子掩码;同时,在图像级检测中,特征按分辨率由高到低逐渐连接丰富信息;最后引入焦点损失来降低类别不平衡对模型带来的影响,对不同分辨率下的掩码进行同等权重监督.实验结果表明,论文提出的检测方法在公开数据集像素级与图像级的检测结果中优于现有方法,验证了注意力机制和渐进式特征连接的有效性.

Materials,Language,and Definitions:On the Differences and Causes of Opinions Regarding the Dating of Laozi in Chinese and Western Academia

The exact dating of Laozi and his work has long been a topic of scholarly interest.Since the 1920s,traditional views on Laozi’s dating have been widely questioned in both Chinese and Western academia.In the latter half of the 20th century,as the“Trust Antiquity”trend gradually emerged in Chinese academia,the view that“Laozi did not exist”became the most influential mainstream perspective in Western academia.This paper first reviews the process of unification and differentiation of opinions between Chinese and Western academia.Then,by analyzing and comparing representative papers from Chinese and Western scholars,it explores the reasons for the differences in mainstream opinions.Additionally,it briefly discusses the implications of these differences to provide insights for future research.

Sora等生成式人工智能对诈骗犯罪司法认定的影响与应对

文生视频大模型Sora是目前生成式人工智能中最为先进的代表性应用。在为人类社会带来福祉及革命性变化的同时,Sora等生成式人工智能技术也有存在可能被滥用于进行“深度伪造”的潜在风险。在刑法层面,“深度伪造”等技术风险使得“眼见耳闻”不再为实,主要可能影响到诈骗类犯罪的司法认定与刑事归责。Sora等生成式人工智能现阶段仍属于弱人工智能,本质上属于人类使用的工具,不具有刑事责任主体资格。在未来的迭代版本中,我们不能排除Sora等生成式人工智能产生自主意识进而成为强人工智能的可能性。在Sora等生成式人工智能的介入下,司法机关将面临前所未有的证据认定难题。Sora等生成式人工智能技术风险的协同治理必须由国家、社会和企业等多方主体共同参与,在技术研发、推广应用等多环节建立健全监督评估机制,并且由行政法、刑法等多个部门法共同规制。