Related papers: Temporal Unlearnable Examples: Preventing Personal…

Adversarial attack arises due to the vulnerability of deep neural networks to perceive input samples injected with imperceptible perturbations. Recently, adversarial attack has been applied to visual object tracking to evaluate the…

How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template…

Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a…

In this paper, we propose to learn temporal embeddings of video frames for complex video analysis. Large quantities of unlabeled video data can be easily obtained from the Internet. These videos possess the implicit weak label that they are…

Deep hash-based retrieval techniques are widely used in facial retrieval systems to improve the efficiency of facial matching. However, it also carries the danger of exposing private information. Deep hash models are easily influenced by…

With an ever-increasing reliance on machine learning (ML) models in the real world, adversarial examples threaten the safety of AI-based systems such as autonomous vehicles. In the image domain, they represent maliciously perturbed data…

Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for training models with broad, general capabilities for text, images, and other modalities. However, for many sequential decision domains such as…

We propose an adversarial learning framework that deals with the privacy-utility tradeoff problem under two types of conditions: data-type ignorant, and data-type aware. Under data-type aware conditions, the privacy mechanism provides a…

Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…

Optimized scene representation is an important characteristic of a framework for detecting abnormalities on live videos. One of the challenges for detecting abnormalities in live videos is real-time detection of objects in a non-parametric…

It is well known that the quality and quantity of training data are significant factors which affect the development and performance of machine intelligence algorithms. Without representative data, neither scientists nor algorithms would be…

The proliferation of powerful Text-to-Video (T2V) models, trained on massive web-scale datasets, raises urgent concerns about copyright and privacy violations. Membership inference attacks (MIAs) provide a principled tool for auditing such…

In action understanding in indoor, we have to recognize human pose and action considering privacy. Although camera images can be used for highly accurate human action recognition, camera images do not preserve privacy. Therefore, we propose…

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data,…

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural…

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…

The rapid expansion of AI in healthcare has led to a surge in medical data generation and storage, boosting medical AI development. However, fears of unauthorized use, like training commercial AI models, hinder researchers from sharing…

We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps. Our architecture achieves temporal stability of the resulting alpha mattes by using…

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…