PyTorchKR Papers

최신 논문

총 37편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2206.09379

0/1 Deep Neural Networks via Block Coordinate Descent

The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity and no viable information of subgradients) impede its development for several decades. Even if there is an impressive body of work on designing DNNs with continuous activation functions that can be deemed as surrogates of the step function, it is still in the possession of some advantageous properties, such as complete robustness to outliers and being capable of attaining the best learning-theoretic guarantee of predictive accuracy. Hence, in this paper, we aim to train DNNs with the step function used as an activation function (dubbed as 0/1 DNNs). We first reformulate 0/1 DNNs as an unconstrained optimization problem and then solve it by a block coordinate descend (BCD) method. Moreover, we acquire closed-form solutions for sub-problems of BCD as well as its convergence properties. Furthermore, we also integrate $\ell_{2,0}$-regularization into 0/1 DNN to accelerate the training process and compress the network scale. As a result, the proposed algorithm has a high performance on classifying MNIST and Fashion-MNIST datasets. As a result, the proposed algorithm has a desirable performance on classifying MNIST, FashionMNIST, Cifar10, and Cifar100 datasets.

arXiv:2110.09795

Geo-DefakeHop: High-Performance Geographic Fake Image Detection

A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work. Geo-DefakeHop is developed based on the parallel subspace learning (PSL) methodology. PSL maps the input image space into several feature subspaces using multiple filter banks. By exploring response differences of different channels between real and fake images for a filter bank, Geo-DefakeHop learns the most discriminant channels and uses their soft decision scores as features. Then, Geo-DefakeHop selects a few discriminant features from each filter bank and ensemble them to make a final binary decision. Geo-DefakeHop offers a light-weight high-performance solution to fake satellite images detection. Its model size is analyzed, which ranges from 0.8 to 62K parameters. Furthermore, it is shown by experimental results that it achieves an F1-score higher than 95\% under various common image manipulations such as resizing, compression and noise corruption.

arXiv:2110.03290

MC-LCR: Multi-modal contrastive classification by locally correlated representations for effective face forgery detection

As the remarkable development of facial manipulation technologies is accompanied by severe security concerns, face forgery detection has become a recent research hotspot. Most existing detection methods train a binary classifier under global supervision to judge real or fake. However, advanced manipulations only perform small-scale tampering, posing challenges to comprehensively capture subtle and local forgery artifacts, especially in high compression settings and cross-dataset scenarios. To address such limitations, we propose a novel framework named Multi-modal Contrastive Classification by Locally Correlated Representations(MC-LCR), for effective face forgery detection. Instead of specific appearance features, our MC-LCR aims to amplify implicit local discrepancies between authentic and forged faces from both spatial and frequency domains. Specifically, we design the shallow style representation block that measures the pairwise correlation of shallow feature maps, which encodes local style information to extract more discriminative features in the spatial domain. Moreover, we make a key observation that subtle forgery artifacts can be further exposed in the patch-wise phase and amplitude spectrum and exhibit different clues. According to the complementarity of amplitude and phase information, we develop a patch-wise amplitude and phase dual attention module to capture locally correlated inconsistencies with each other in the frequency domain. Besides the above two modules, we further introduce the collaboration of supervised contrastive loss with cross-entropy loss. It helps the network learn more discriminative and generalized representations. Through extensive experiments and comprehensive studies, we achieve state-of-the-art performance and demonstrate the robustness and generalization of our method.

arXiv:2106.08749

Learning to Disentangle GAN Fingerprint for Fake Image Attribution

Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake image attribution. Existing works on fake image attribution mainly rely on a direct classification framework. Without additional supervision, the extracted features could include many content-relevant components and generalize poorly. Meanwhile, how to obtain an interpretable GAN fingerprint to explain the decision remains an open question. Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Network (GFD-Net) to simultaneously disentangle the fingerprint from GAN-generated images and produce a content-irrelevant representation for fake image attribution. A series of constraints are provided to guarantee the stability and discriminability of the fingerprint, which in turn helps content-irrelevant feature extraction. Further, we perform comprehensive analysis on GAN fingerprint, providing some clues about the properties of GAN fingerprint and which factors dominate the fingerprint in GAN architecture. Experiments show that our GFD-Net achieves superior fake image attribution performance in both closed-world and open-world testing. We also apply our method in binary fake image detection and exhibit a significant generalization ability on unseen generators.

arXiv:2106.01615

Imperceptible Adversarial Examples for Fake Image Detection

Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society. Many methods have been proposed to detect fake images, but they are vulnerable to adversarial perturbations -- intentionally designed noises that can lead to the wrong prediction. Existing methods of attacking fake image detectors usually generate adversarial perturbations to perturb almost the entire image. This is redundant and increases the perceptibility of perturbations. In this paper, we propose a novel method to disrupt the fake image detection by determining key pixels to a fake image detector and attacking only the key pixels, which results in the $L_0$ and the $L_2$ norms of adversarial perturbations much less than those of existing works. Experiments on two public datasets with three fake image detectors indicate that our proposed method achieves state-of-the-art performance in both white-box and black-box attacks.

arXiv:2102.01313

Fake-image detection with Robust Hashing

In this paper, we investigate whether robust hashing has a possibility to robustly detect fake-images even when multiple manipulation techniques such as JPEG compression are applied to images for the first time. In an experiment, the proposed fake detection with robust hashing is demonstrated to outperform state-of-the-art one under the use of various datasets including fake images generated with GANs.

arXiv:2012.00287

CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

In this paper, we propose a novel CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection. Recent rapid advances in image manipulation tools and deep image synthesis techniques, such as Generative Adversarial Networks (GANs) have easily generated fake images, so detecting manipulated images has become an urgent issue. Most state-of-the-art forgery detection methods assume that images include checkerboard artifacts which are generated by using DNNs. Accordingly, we propose a novel CycleGAN without any checkerboard artifacts for counter-forensics of fake-mage detection methods for the first time, as an example of GANs without checkerboard artifacts.

arXiv:2009.09213

Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering

The current high-fidelity generation and high-precision detection of DeepFake images are at an arms race. We believe that producing DeepFakes that are highly realistic and 'detection evasive' can serve the ultimate goal of improving future generation DeepFake detection capabilities. In this paper, we propose a simple yet powerful pipeline to reduce the artifact patterns of fake images without hurting image quality by performing implicit spatial-domain notch filtering. We first demonstrate that frequency-domain notch filtering, although famously shown to be effective in removing periodic noise in the spatial domain, is infeasible for our task at hand due to the manual designs required for the notch filters. We, therefore, resort to a learning-based approach to reproduce the notch filtering effects, but solely in the spatial domain. We adopt a combination of adding overwhelming spatial noise for breaking the periodic noise pattern and deep image filtering to reconstruct the noise-free fake images, and we name our method DeepNotch. Deep image filtering provides a specialized filter for each pixel in the noisy image, producing filtered images with high fidelity compared to their DeepFake counterparts. Moreover, we also use the semantic information of the image to generate an adversarial guidance map to add noise intelligently. Our large-scale evaluation on 3 representative state-of-the-art DeepFake detection methods (tested on 16 types of DeepFakes) has demonstrated that our technique significantly reduces the accuracy of these 3 fake image detection methods, 36.79% on average and up to 97.02% in the best case.

arXiv:2006.07533

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. However, the existing detection methods put much emphasis on the artifact patterns, which can become futile if such artifact patterns were reduced. Towards reducing the artifacts in the synthesized images, in this paper, we devise a simple yet powerful approach termed FakePolisher that performs shallow reconstruction of fake images through a learned linear dictionary, intending to effectively and efficiently reduce the artifacts introduced during image synthesis. The comprehensive evaluation on 3 state-of-the-art DeepFake detection methods and fake images generated by 16 popular GAN-based fake image generation techniques, demonstrates the effectiveness of our technique.Overall, through reducing artifact patterns, our technique significantly reduces the accuracy of the 3 state-of-the-art fake image detection methods, i.e., 47% on average and up to 93% in the worst case.

arXiv:2004.07676공식 코드 · Papers with Code

Video Face Manipulation Detection Through Ensemble of CNNs

In the last few years, several techniques for facial manipulation in videos have been successfully developed and made available to the masses (i.e., FaceSwap, deepfake, etc.). These methods enable anyone to easily edit faces in video sequences with incredibly realistic results and a very little effort. Despite the usefulness of these tools in many fields, if used maliciously, they can have a significantly bad impact on society (e.g., fake news spreading, cyber bullying through fake revenge porn). The ability of objectively detecting whether a face has been manipulated in a video sequence is then a task of utmost importance. In this paper, we tackle the problem of face manipulation detection in video sequences targeting modern facial manipulation techniques. In particular, we study the ensembling of different trained Convolutional Neural Network (CNN) models. In the proposed solution, different models are obtained starting from a base network (i.e., EfficientNetB4) making use of two different concepts: (i) attention layers; (ii) siamese training. We show that combining these networks leads to promising face manipulation detection results on two publicly available datasets with more than 119000 videos.

arXiv:2002.00133공식 코드 · Papers with Code

Global Texture Enhancement for Fake Face Detection in the Wild

Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings.On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than 99.9% accuracyin discerning fake/real images. In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets. Motivated by the above observations, we propose a new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection. Experimental results on several datasets demonstrate that our Gram-Net outperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEG compression, blur, and noise. More importantly, our Gram-Net generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detecting fake natural images.

arXiv:2001.09598

FakeLocator: Robust Localization of GAN-Based Face Manipulations

Full face synthesis and partial face manipulation by virtue of the generative adversarial networks (GANs) and its variants have raised wide public concerns. In the multi-media forensics area, detecting and ultimately locating the image forgery has become an imperative task. In this work, we investigate the architecture of existing GAN-based face manipulation methods and observe that the imperfection of upsampling methods therewithin could be served as an important asset for GAN-synthesized fake image detection and forgery localization. Based on this basic observation, we have proposed a novel approach, termed FakeLocator, to obtain high localization accuracy, at full resolution, on manipulated facial images. To the best of our knowledge, this is the very first attempt to solve the GAN-based fake localization problem with a gray-scale fakeness map that preserves more information of fake regions. To improve the universality of FakeLocator across multifarious facial attributes, we introduce an attention mechanism to guide the training of the model. To improve the universality of FakeLocator across different DeepFake methods, we propose partial data augmentation and single sample clustering on the training images. Experimental results on popular FaceForensics++, DFFD datasets and seven different state-of-the-art GAN-based face generation methods have shown the effectiveness of our method. Compared with the baselines, our method performs better on various metrics. Moreover, the proposed method is robust against various real-world facial image degradations such as JPEG compression, low-resolution, noise, and blur.

arXiv:1901.08971공식 코드 · Papers with Code

FaceForensics++: Learning to Detect Manipulated Facial Images

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on DeepFakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domainspecific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.

arXiv:1809.08754

Learning to Detect Fake Face Images in the Wild

Although Generative Adversarial Network (GAN) can be used to generate the realistic image, improper use of these technologies brings hidden concerns. For example, GAN can be used to generate a tampered video for specific people and inappropriate events, creating images that are detrimental to a particular person, and may even affect that personal safety. In this paper, we will develop a deep forgery discriminator (DeepFD) to efficiently and effectively detect the computer-generated images. Directly learning a binary classifier is relatively tricky since it is hard to find the common discriminative features for judging the fake images generated from different GANs. To address this shortcoming, we adopt contrastive loss in seeking the typical features of the synthesized images generated by different GANs and follow by concatenating a classifier to detect such computer-generated images. Experimental results demonstrate that the proposed DeepFD successfully detected 94.7% fake images generated by several state-of-the-art GANs.

arXiv:1809.00888공식 코드 · Papers with Code

MesoNet: a Compact Facial Video Forgery Detection Network

This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98% for Deepfake and 95% for Face2Face.

arXiv:2609.24359v1cs.CV

에이전틱 포렌식 분석: 오픈월드 가짜 이미지 탐지에서 분류 선별, 프롬프팅, 증거 중재의 역할

Dissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection

이미지 포렌식은 점점 더 오픈월드(open-world) 문제가 되고 있습니다. 조작의 유형은 완전한 합성 이미지부터 국소적 편집, 이어붙이기(splicing), 바꾸기(swapping)에 이르기까지 다양한 반면, 대부분의 포렌식 탐지기는 여전히 단일 조작 계열에만 특화되어 있습니다. 최근 에이전틱(agentic) AI가 유망한 해결책으로 떠올랐습니다. 원칙적으로 이러한 시스템은 개별 탐지기의 신뢰성을 평가하고, 범위를 벗어난 증거를 식별하며, 상충하는 보고를 중재할 수 있습니다. 그러나 실제로 어떤 구성 요소가 성능을 주도하는지, 그리고 이들의 이점이 분포 변화(distribution shift) 하에서도 유지되는지는 여전히 불분명합니다. 이러한 질문에 답하기 위해, 본 연구에서는 전문 탐지기, 탐지기별 분류 선별(triage), 충돌 인지형 증거 중재를 중심으로 구축된 학습(training) 불필요(training-free) 에이전틱 프레임워크를 연구합니다. 6가지 구성과 3가지 멀티모달 대규모 언어 모델(multimodal LLM) 백본을 사용하여, 분포 내(in-distribution) 및 분포 외(out-of-distribution) 데이터 모두에서 분류 선별, 프롬프팅, 추론 품질의 역할을 분석합니다. 실험 결과에 따르면 단순한 탐지기 융합은 진본 이미지에 대해 심각한 위양성률(false-positive rate)을 겪는 것으로 나타났습니다. 분류 선별과 프롬프팅은 신뢰할 수 없는 증거를 필터링하고 탐지기의 한계를 드러냄으로써 성능을 일관되게 향상시킵니다. 그러나 가장 지배적인 요인은 추론 자체로 나타납니다. 더 강력한 판별자(judge)는 특히 분포 변화 환경에서 더 약한 판별자보다 실질적으로 우수한 성능을 보입니다. 가장 주목할 점은 모든 구성에서 조작 재현율(recall)이 거의 포화 상태에 도달했다는 점이며, 이는 오픈월드 이미지 포렌식의 주요 과제가 조작을 탐지하는 것이 아니라 특화된 포렌식 도구에 대한 신뢰도를 보정하고 상충하는 증거를 중재하는 것임을 시사합니다.

arXiv:2607.22087v1cs.CV

FAIR: AI 생성 가짜 이미지 탐지를 위한 특징 증강 암시적 정규화

FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection

AI 생성 이미지 탐지에서 일반화는 여전히 핵심 병목이다. 많은 최신 생성기가 독점적이거나 적대적으로 수정되어 있기 때문에, 기존 탐지기는 접근 가능한 학습 데이터의 저수준 텍스처 패턴에 과적합되어, 보지 못한 도메인에서 심각한 실패를 초래한다. 기존 정규화 기법(예: $L_1$/$L_2$ 노름, 드롭아웃)은 무차별적인 파라미터 제약을 적용하며, 생성기 간 견고성에 필요한 도메인 불변 구조를 제공하지 못한다. 이를 해결하기 위해, 우리는 Feature-Augmented Implicit Regularization(FAIR)을 제안한다. FAIR은 학습 중에 직교적이고 거시적 구조 사전(prior), 구체적으로 Scene Composition Structure(SCS)를 도입하여 모델의 최적화 궤적을 기하학적으로 제약한다. 도메인 불변 SCS 특징으로 주요 특징 공간을 증강함으로써, FAIR은 텍스처 편향 단축 학습을 명시적으로 억제한다. 중요하게도, 이 구조적 사전은 추론 시 완전히 폐기되어, 아키텍처 또는 계산 오버헤드 없이 평활화되고 일반화된 결정 경계를 제공한다. 다섯 개의 대규모 벤치마크에 걸친 광범위한 평가는 FAIR을 최신 탐지기에 통합하면 생성기 간 일반화가 크게 향상되어 정확도가 최대 8.04%까지 증가하고, 제로샷 전이 시나리오에서 새로운 최첨단 견고성을 확립함을 보여준다.