Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN

• URL: http://arxiv.org/abs/2310.08371v2
• Date: Fri, 13 Oct 2023 09:20:09 GMT
• Title: Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN
• Authors: Una M. Kelly, Meike Nauta, Lu Liu, Luuk J. Spreeuwers, Raymond N. J. Veldhuis
• Abstract summary: We introduce a morph generation method that can approximate worst-case morphs even when the Face Recognition system is not known. Our method is based on Adversarially Learned Inference (ALI) and uses concepts from Wasserstein GANs trained with Gradient Penalty. We show how our findings can be used to improve MIPGAN, an existing StyleGAN-based morph generator.
• Score: 5.1899190294312385
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both people can be authenticated by a biometric Face Recognition (FR) system. Morphs can be generated using either a landmark-based approach or approaches based on deep learning such as Generative Adversarial Networks (GAN). In a recent paper, we introduced a \emph{worst-case} upper bound on how challenging morphing attacks can be for an FR system. The closer morphs are to this upper bound, the bigger the challenge they pose to FR. We introduced an approach with which it was possible to generate morphs that approximate this upper bound for a known FR system (white box), but not for unknown (black box) FR systems. In this paper, we introduce a morph generation method that can approximate worst-case morphs even when the FR system is not known. A key contribution is that we include the goal of generating difficult morphs \emph{during} training. Our method is based on Adversarially Learned Inference (ALI) and uses concepts from Wasserstein GANs trained with Gradient Penalty, which were introduced to stabilise the training of GANs. We include these concepts to achieve similar improvement in training stability and call the resulting method Wasserstein ALI (WALI). We finetune WALI using loss functions designed specifically to improve the ability to manipulate identity information in facial images and show how it can generate morphs that are more challenging for FR systems than landmark- or GAN-based morphs. We also show how our findings can be used to improve MIPGAN, an existing StyleGAN-based morph generator.

Related papers

• MLSD-GAN -- Generating Strong High Quality Face Morphing Attacks using Latent Semantic Disentanglement [6.747633314364796]
  Face-morphing attacks can be used to fool face recognition systems. We propose a new method for generating high-quality morphing attacks using StyleGAN disentanglement.
  arXiv  Detail & Related papers  (2024-04-19T07:26:30Z)
• SDeMorph: Towards Better Facial De-morphing from Single Morph [0.0]
  Face Recognition Systems (FRS) are vulnerable to morph attacks. Current Morph Attack Detection (MAD) can detect the morph but are unable to recover the identities used to create the morph. We propose SDeMorph, a novel de-morphing method that is reference-free and recovers the identities of bona fides.
  arXiv  Detail & Related papers  (2023-08-22T13:46:12Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• MorphGANFormer: Transformer-based Face Morphing and De-Morphing [55.211984079735196]
  StyleGAN-based approaches to face morphing are among the leading techniques. We propose a transformer-based alternative to face morphing and demonstrate its superiority to StyleGAN-based methods.
  arXiv  Detail & Related papers  (2023-02-18T19:09:11Z)
• Landmark Enforcement and Style Manipulation for Generative Morphing [24.428843425522107]
  We propose a novel StyleGAN morph generation technique by introducing a landmark enforcement method to resolve this issue. Exploration of the latent space of our model is conducted using Principal Component Analysis (PCA) to accentuate the effect of both the bona fide faces on the morphed latent representation. To improve high frequency reconstruction in the morphs, we study the train-ability of the noise input for the StyleGAN2 model.
  arXiv  Detail & Related papers  (2022-10-18T22:10:25Z)
• StyleSwap: Style-Based Generator Empowers Robust Face Swapping [90.05775519962303]
  We introduce a concise and effective framework named StyleSwap. Our core idea is to leverage a style-based generator to empower high-fidelity and robust face swapping. We identify that with only minimal modifications, a StyleGAN2 architecture can successfully handle the desired information from both source and target.
  arXiv  Detail & Related papers  (2022-09-27T16:35:16Z)
• MobileFaceSwap: A Lightweight Framework for Video Face Swapping [56.87690462046143]
  We propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping. The presented IDN contains only 0.50M parameters and needs 0.33G FLOPs per frame, making it capable for real-time video face swapping on mobile phones.
  arXiv  Detail & Related papers  (2022-01-11T06:48:12Z)
• A Face Recognition System's Worst Morph Nightmare, Theoretically [0.0]
  Face Recognition Systems (FRSs) are vulnerable to morphing attacks, but most research focusses on landmark-based morphs. We propose a method to create a third, different type of morph, that has the advantage of being easier to train.
  arXiv  Detail & Related papers  (2021-11-30T14:09:47Z)
• My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control [65.77164390203396]
  We present a series of ablations on existing methods that show that morphological information encoded in the graph does not improve their performance. Motivated by the hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing, we also propose Amorpheus.
  arXiv  Detail & Related papers  (2020-10-05T08:37:11Z)
• Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? -- Vulnerability and Detection [22.220940043294334]
  We propose a new framework for generating face morphs using a newer Generative Adversarial Network (GAN) - StyleGAN. With the newly created morphing dataset of 2500 morphed face images, we pose a critical question in this work.
  arXiv  Detail & Related papers  (2020-07-07T16:52:56Z)
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition [94.96686189033869]
  We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
  arXiv  Detail & Related papers  (2020-02-23T08:16:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.