Related papers: Ulixes: Facial Recognition Privacy with Adversaria…

For the time being, mobile devices employ implicit authentication mechanisms, namely, unlock patterns, PINs or biometric-based systems such as fingerprint or face recognition. While these systems are prone to well-known attacks, the…

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Contrastive learning is widely used for recommendation model learning, where selecting representative and informative negative samples is critical. Existing methods usually focus on centralized data, where abundant and high-quality negative…

Image data have been extensively used in Deep Neural Network (DNN) tasks in various scenarios, e.g., autonomous driving and medical image analysis, which incurs significant privacy concerns. Existing privacy protection techniques are unable…

Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-based methods mainly focus on the de-identification against…

The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on social media. Several attempts have been made to protect…

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…

Face identity masking algorithms developed in recent years aim to protect the privacy of people in video recordings. These algorithms are designed to interfere with identification, while preserving information about facial actions. An…

Personalized text-to-image models allow users to generate images of new concepts from several reference photos, thereby leading to critical concerns regarding civil privacy. Although several anti-personalization techniques have been…

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint…

In many real-world applications, face recognition models often degenerate when training data (referred to as source domain) are different from testing data (referred to as target domain). To alleviate this mismatch caused by some factors…

Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performance in detecting fake images from real ones, these models can…

Deep learning has been broadly leveraged by major cloud providers, such as Google, AWS and Baidu, to offer various computer vision related services including image classification, object identification, illegal image detection, etc. While…

Recent years have seen fast development in synthesizing realistic human faces using AI technologies. Such fake faces can be weaponized to cause negative personal and social impact. In this work, we develop technologies to defend individuals…

Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…

Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art…

This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseudo labels and use the produced labels to train Re-ID models…

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…