Abstract:Adversarial attacks on Face Recognition (FR) systems have proven highly effective in compromising pure FR models, yet adversarial examples may be ineffective to the complete FR systems as Face Anti-Spoofing (FAS) models are often incorporated and can detect a significant number of them. To address this under-explored and essential problem, we propose a novel setting of adversarially attacking both FR and FAS models simultaneously, aiming to enhance the practicability of adversarial attacks on FR systems. In particular, we introduce a new attack method, namely Style-aligned Distribution Biasing (SDB), to improve the capacity of black-box attacks on both FR and FAS models. Specifically, our SDB framework consists of three key components. Firstly, to enhance the transferability of FAS models, we design a Distribution-aware Score Biasing module to optimize adversarial face examples away from the distribution of spoof images utilizing scores. Secondly, to mitigate the substantial style differences between live images and adversarial examples initialized with spoof images, we introduce an Instance Style Alignment module that aligns the style of adversarial examples with live images. In addition, to alleviate the conflicts between the gradients of FR and FAS models, we propose a Gradient Consistency Maintenance module to minimize disparities between the gradients using Hessian approximation. Extensive experiments showcase the superiority of our proposed attack method to state-of-the-art adversarial attacks.
Abstract:As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data. Although previous detection methods achieve high performance in detecting gradient-based adversarial attacks, new attacks based on generative models with imbalanced and anisotropic noise patterns evade detection. Even worse, existing techniques either necessitate access to attack data before deploying a defense or incur a significant time cost for inference, rendering them impractical for defending against newly emerging attacks that are unseen by defenders. In this paper, we explore the proximity relationship between adversarial noise distributions and demonstrate the existence of an open covering for them. By learning to distinguish this open covering from the distribution of natural data, we can develop a detector with strong generalization capabilities against all types of adversarial attacks. Based on this insight, we heuristically propose Perturbation Forgery, which includes noise distribution perturbation, sparse mask generation, and pseudo-adversarial data production, to train an adversarial detector capable of detecting unseen gradient-based, generative-model-based, and physical adversarial attacks, while remaining agnostic to any specific models. Comprehensive experiments conducted on multiple general and facial datasets, with a wide spectrum of attacks, validate the strong generalization of our method.
Abstract:Digital watermarking is the process of embedding secret information by altering images in a way that is undetectable to the human eye. To increase the robustness of the model, many deep learning-based watermarking methods use the encoder-decoder architecture by adding different noises to the noise layer. The decoder then extracts the watermarked information from the distorted image. However, this method can only resist weak noise attacks. To improve the robustness of the algorithm against stronger noise, this paper proposes to introduce a denoise module between the noise layer and the decoder. The module is aimed at reducing noise and recovering some of the information lost during an attack. Additionally, the paper introduces the SE module to fuse the watermarking information pixel-wise and channel dimensions-wise, improving the encoder's efficiency. Experimental results show that our proposed method is comparable to existing models and outperforms state-of-the-art under different noise intensities. In addition, ablation experiments show the superiority of our proposed module.
Abstract:Embedding invisible hyperlinks or hidden codes in images to replace QR codes has become a hot topic recently. This technology requires first localizing the embedded region in the captured photos before decoding. Existing methods that train models to find the invisible embedded region struggle to obtain accurate localization results, leading to degraded decoding accuracy. This limitation is primarily because the CNN network is sensitive to low-frequency signals, while the embedded signal is typically in the high-frequency form. Based on this, this paper proposes a Dual-Branch Dual-Head (DBDH) neural network tailored for the precise localization of invisible embedded regions. Specifically, DBDH uses a low-level texture branch containing 62 high-pass filters to capture the high-frequency signals induced by embedding. A high-level context branch is used to extract discriminative features between the embedded and normal regions. DBDH employs a detection head to directly detect the four vertices of the embedding region. In addition, we introduce an extra segmentation head to segment the mask of the embedding region during training. The segmentation head provides pixel-level supervision for model learning, facilitating better learning of the embedded signals. Based on two state-of-the-art invisible offline-to-online messaging methods, we construct two datasets and augmentation strategies for training and testing localization models. Extensive experiments demonstrate the superior performance of the proposed DBDH over existing methods.
Abstract:Modern image processing tools have made it easy for attackers to crop the region or object of interest in images and paste it into other images. The challenge this cropping-paste attack poses to the watermarking technology is that it breaks the synchronization of the image watermark, introducing multiple superimposed desynchronization distortions, such as rotation, scaling, and translation. However, current watermarking methods can only resist a single type of desynchronization and cannot be applied to protect the object's copyright under the cropping-paste attack. With the finding that the key to resisting the cropping-paste attack lies in robust features of the object to protect, this paper proposes a self-synchronizing object-aligned watermarking method, called SSyncOA. Specifically, we first constrain the watermarked region to be aligned with the protected object, and then synchronize the watermark's translation, rotation, and scaling distortions by normalizing the object invariant features, i.e., its centroid, principal orientation, and minimum bounding square, respectively. To make the watermark embedded in the protected object, we introduce the object-aligned watermarking model, which incorporates the real cropping-paste attack into the encoder-noise layer-decoder pipeline and is optimized end-to-end. Besides, we illustrate the effect of different desynchronization distortions on the watermark training, which confirms the necessity of the self-synchronization process. Extensive experiments demonstrate the superiority of our method over other SOTAs.
Abstract:JPEG compression can significantly impair the performance of adversarial face examples, which previous adversarial attacks on face recognition (FR) have not adequately addressed. Considering this challenge, we propose a novel adversarial attack on FR that aims to improve the resistance of adversarial examples against JPEG compression. Specifically, during the iterative process of generating adversarial face examples, we interpolate the adversarial face examples into a smaller size. Then we utilize these interpolated adversarial face examples to create the adversarial examples in the next iteration. Subsequently, we restore the adversarial face examples to their original size by interpolating. Throughout the entire process, our proposed method can smooth the adversarial perturbations, effectively mitigating the presence of high-frequency signals in the crafted adversarial face examples that are typically eliminated by JPEG compression. Our experimental results demonstrate the effectiveness of our proposed method in improving the JPEG-resistance of adversarial face examples.
Abstract:In response to the rapidly evolving nature of adversarial attacks on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that can generalize to all types of attacks, including unseen ones, is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks used by many attackers. The defense system needs to upgrade itself by utilizing few-shot defense feedback and efficient memory. Therefore, we propose the first continual adversarial defense (CAD) framework that adapts to any attacks in a dynamic scenario, where various attacks emerge stage by stage. In practice, CAD is modeled under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial images. We leverage cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Experiments conducted on CIFAR-10 and ImageNet-100 validate the effectiveness of our approach against multiple stages of 10 modern adversarial attacks and significant improvements over 10 baseline methods. In particular, CAD is capable of quickly adapting with minimal feedback and a low cost of defense failure, while maintaining good performance against old attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Abstract:Adversarial face examples possess two critical properties: Visual Quality and Transferability. However, existing approaches rarely address these properties simultaneously, leading to subpar results. To address this issue, we propose a novel adversarial attack technique known as Adversarial Restoration (AdvRestore), which enhances both visual quality and transferability of adversarial face examples by leveraging a face restoration prior. In our approach, we initially train a Restoration Latent Diffusion Model (RLDM) designed for face restoration. Subsequently, we employ the inference process of RLDM to generate adversarial face examples. The adversarial perturbations are applied to the intermediate features of RLDM. Additionally, by treating RLDM face restoration as a sibling task, the transferability of the generated adversarial face examples is further improved. Our experimental results validate the effectiveness of the proposed attack method.
Abstract:Adversarial attacks aim to disturb the functionality of a target system by adding specific noise to the input samples, bringing potential threats to security and robustness when applied to facial recognition systems. Although existing defense techniques achieve high accuracy in detecting some specific adversarial faces (adv-faces), new attack methods especially GAN-based attacks with completely different noise patterns circumvent them and reach a higher attack success rate. Even worse, existing techniques require attack data before implementing the defense, making it impractical to defend newly emerging attacks that are unseen to defenders. In this paper, we investigate the intrinsic generality of adv-faces and propose to generate pseudo adv-faces by perturbing real faces with three heuristically designed noise patterns. We are the first to train an adv-face detector using only real faces and their self-perturbations, agnostic to victim facial recognition systems, and agnostic to unseen attacks. By regarding adv-faces as out-of-distribution data, we then naturally introduce a novel cascaded system for adv-face detection, which consists of training data self-perturbations, decision boundary regularization, and a max-pooling-based binary classifier focusing on abnormal local color aberrations. Experiments conducted on LFW and CelebA-HQ datasets with eight gradient-based and two GAN-based attacks validate that our method generalizes to a variety of unseen adversarial attacks.
Abstract:Face recognition (FR) models can be easily fooled by adversarial examples, which are crafted by adding imperceptible perturbations on benign face images. To improve the transferability of adversarial examples on FR models, we propose a novel attack method called Beneficial Perturbation Feature Augmentation Attack (BPFA), which reduces the overfitting of the adversarial examples to surrogate FR models by the adversarial strategy. Specifically, in the backpropagation step, BPFA records the gradients on pre-selected features and uses the gradient on the input image to craft adversarial perturbation to be added on the input image. In the next forward propagation step, BPFA leverages the recorded gradients to add perturbations(i.e., beneficial perturbations) that can be pitted against the adversarial perturbation added on the input image on their corresponding features. The above two steps are repeated until the last backpropagation step before the maximum number of iterations is reached. The optimization process of the adversarial perturbation added on the input image and the optimization process of the beneficial perturbations added on the features correspond to a minimax two-player game. Extensive experiments demonstrate that BPFA outperforms the state-of-the-art gradient-based adversarial attacks on FR.