Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News

Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem. Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism. While existing approaches have been proposed to defend against neural fake news, they are generally constrained to the very limited setting where articles only have text and metadata such as the title and authors. In this paper, we introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles as well as conduct a series of human user study experiments based on this dataset. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies, which will serve as an effective first line of defense and a useful reference for future work in defending against machine-generated disinformation.

[1]  Andrew Owens,et al.  Detecting Photoshopped Faces by Scripting Photoshop , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Ali Farhadi,et al.  Defending Against Neural Fake News , 2019, NeurIPS.

[4]  Xin Yang,et al.  Exposing Deep Fakes Using Inconsistent Head Poses , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Robert Chesney,et al.  Deepfakes and the New Disinformation War , 2018 .

[6]  Jungong Han,et al.  Saliency-Guided Attention Network for Image-Sentence Matching , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Xi Chen,et al.  Stacked Cross Attention for Image-Text Matching , 2018, ECCV.

[8]  Robert M. Chesney,et al.  Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security , 2018 .

[9]  Hao Li,et al.  Protecting World Leaders Against Deep Fakes , 2019, CVPR Workshops.

[10]  Lei Zhang,et al.  Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Jiebo Luo,et al.  A Fast and Accurate One-Stage Approach to Visual Grounding , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  Christian Riess,et al.  Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations , 2019, 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW).

[13]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[14]  Svetlana Lazebnik,et al.  Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[16]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[18]  Junichi Yamagishi,et al.  Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection , 2019, AINA.

[19]  Dimosthenis Karatzas,et al.  Good News, Everyone! Context Driven Entity-Aware Captioning for News Images , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Andrew Owens,et al.  CNN-Generated Images Are Surprisingly Easy to Spot… for Now , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Sanja Fidler,et al.  Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[23]  Yonghui Wu,et al.  Exploring the Limits of Language Modeling , 2016, ArXiv.

[24]  Andrew Tomkins,et al.  Reverse Engineering Configurations of Neural Text Generation Models , 2020, ACL.

[25]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[27]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[28]  Pawan Goyal,et al.  A Dataset for Sanskrit Word Segmentation , 2017, LaTeCH@ACL.

[29]  Yisroel Mirsky,et al.  The Creation and Detection of Deepfakes , 2020, ACM Comput. Surv..