The ever-growing threat of deepfakes and large-scale societal implications has propelled the development of deepfake forensics to ascertain the trustworthiness of digital media. A common theme of existing detection methods is using Convolutional Neural Networks (CNNs) as a backbone. While CNNs have demonstrated decent performance on learning local discriminative information, they fail to learn relative spatial features and lose important information due to constrained receptive fields. Motivated by the aforementioned challenges, this work presents DFDT, an end-to-end deepfake detection framework that leverages the unique characteristics of transformer models, for learning hidden traces of perturbations from both local image features and global relationship of pixels at different forgery scales. DFDT is specifically designed for deepfake detection tasks consisting of four main components: patch extraction & embedding, multi-stream transformer block, attention-based patch selection followed by a multi-scale classifier. DFDT’s transformer layer benefits from a re-attention mechanism instead of a traditional multi-head self-attention layer. To evaluate the performance of DFDT, a comprehensive set of experiments are conducted on several deepfake forensics benchmarks. Obtained results demonstrated the surpassing detection rate of DFDT, achieving 99.41%, 99.31%, and 81.35% on FaceForensics++, Celeb-DF (V2), and WildDeepfake, respectively. Moreover, DFDT’s excellent cross-dataset & cross-manipulation generalization provides additional strong evidence on its effectiveness.

Recent advancements of Generative Adversarial Networks (GANs) pose emerging yet serious privacy risks threatening digital media’s integrity and trustworthiness, specifically digital video, through synthesizing hyper-realistic images and videos, i.e., DeepFakes. The need for ascertaining the trustworthiness of digital media calls for automatic yet accurate DeepFake detection algorithms. This paper presents an attention-based DeepFake detection (ADD) method that exploits the fine-grained and spatial locality attributes of artificially synthesized videos for enhanced detection. ADD framework is composed of two main components including face close-up and face shut-off data augmentation methods and is applicable to any classifier based on convolutional neural network architecture. ADD first locates potentially manipulated areas of the input image to extract representative features. Second, the detection model is forced to pay more attention to these forgery regions in the decision-making process through a particular focus on interpreting the sample in the learning phase. ADD’s performance is evaluated against two challenging datasets of DeepFake forensics, i.e., Celeb-DF (V2) and WildDeepFake. We demonstrated the generalization of ADD by evaluating four popular classifiers, namely VGGNet, ResNet, Xception, and MobileNet. The obtained results demonstrate that ADD can boost the detection performance of all four baseline classifiers significantly on both benchmark datasets. Particularly, ADD with ResNet backbone detects DeepFakes with more than 98.3% on Celeb-DF (V2), outperforming state-of-the-art DeepFake detection methods.

Deep learning’s automatic feature extraction has proven its superior performance over traditional fingerprint-based features in the implementation of virtual screening models. However, these models face multiple challenges in the field of early drug discovery, such as over-training and generalization to unseen data, due to the inherently unbalanced and small datasets. In this work, the TranScreen pipeline is proposed, which utilizes transfer learning and a collection of weight initializations to overcome these challenges. An amount of 182 graph convolutional neural networks are trained on molecular source datasets and the learned knowledge is transferred to the target task for fine-tuning. The target task of p53-based bioactivity prediction, an important factor for anti-cancer discovery, is chosen to showcase the capability of the pipeline. Having trained a collection of source models, three different approaches are implemented to compare and rank them for a given task before fine-tuning. The results show improvement in performance of the model in multiple cases, with the best model increasing the area under receiver operating curve ROC-AUC from 0.75 to 0.91 and the recall from 0.25 to 1. This improvement is vital for practical virtual screening via lowering the false negatives and demonstrates the potential of transfer learning. The code and pre-trained models are made accessible online.

In this work, we propose a novel defense system against adversarial examples leveraging the unique power of Generative Adversarial Networks (GANs) to generate new adversarial examples for model retraining. To do so, we develop an automated pipeline using combination of pre-trained convolutional neural network and an external GAN, that is, Pix2Pix conditional GAN, to determine the transformations between adversarial examples and clean data, and to automatically synthesize new adversarial examples. These adversarial examples are employed to strengthen the model, attack, and defense in an iterative pipeline. Our simulation results demonstrate the success of the proposed method.

Despite many attempts, the state-of-the-art of adversarial machine learning on malware detection systems generally yield unexecutable samples. In this work, we set out to examine the robustness of visualization-based malware detection system against adversarial examples (AEs) that not only are able to fool the model, but also maintain the executability of the original input. As such, we first investigate the application of existing off-the-shelf adversarial attack approaches on malware detection systems through which we found that those approaches do not necessarily maintain the functionality of the original inputs. Therefore, we proposed an approach to generate adversarial examples, COPYCAT, which is specifically designed for malware detection systems considering two main goals; achieving a high misclassification rate and maintaining the executability and functionality of the original input. We designed two main configurations for COPYCAT, namely AE padding and sample injection. While the first configuration results in untargeted misclassification attacks, the sample injection configuration is able to force the model to generate a targeted output, which is highly desirable in the malware attribution setting. We evaluate the performance of COPYCAT through an extensive set of experiments on two malware datasets, and report that we were able to generate adversarial samples that are misclassified at a rate of 98.9% and 96.5% with Windows and IoT binary datasets, respectively, outperforming the misclassification rates in the literature. Most importantly, we report that those AEs were executable unlike AEs generated by off-the-shelf approaches. Our transferability study demonstrates that the generated AEs through our proposed method can be generalized to other models.

Deep learning models are widely used in a range of application areas, such as computer vision, computer security, etc. However, deep learning models are vulnerable to Adversarial Examples (AEs),carefully crafted samples to deceive those models. Recent studies have introduced new adversarial attack methods, but, to the best of our knowledge, none provided guaranteed quality for the crafted examples as part of their creation, beyond simple quality measures such as Misclassification Rate (MR). In this paper, we incorporateImage Quality Assessment (IQA) metrics into the design and generation process of AEs. We propose an evolutionary-based single- and multi-objective optimization approaches that generate AEs with high misclassification rate and explicitly improve the quality, thus indistinguishability, of the samples, while perturbing only a limited number of pixels. In particular, several IQA metrics, including edge analysis, Fourier analysis, and feature descriptors, are leveraged into the process of generating AEs. Unique characteristics of the evolutionary-based algorithm enable us to simultaneously optimize the misclassification rate and the IQA metrics of the AEs. In order to evaluate the performance of the proposed method, we conduct intensive experiments on different well-known benchmark datasets(MNIST, CIFAR, GTSRB, and Open Image Dataset V5), while considering various objective optimization configurations. The results obtained from our experiments, when compared with the exist-ing attack methods, validate our initial hypothesis that the use ofIQA metrics within generation process of AEs can substantially improve their quality, while maintaining high misclassification rate.Finally, transferability and human perception studies are provided, demonstrating acceptable performance.