Related papers: CLOAK: Contrastive Guidance for Latent Diffusion-B…

Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse…

The Industrial Internet of Things (IIoT) integrates intelligent sensing, communication, and analytics into industrial environments, including manufacturing, energy, and critical infrastructure. While IIoT enables predictive maintenance and…

We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction. We term this approach \emph{Privacy…

We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models…

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability. One flourishing approach is through counterfactual explanations, which provide…

The inexorable growth of online shopping and e-commerce demands scalable and robust machine learning-based solutions to accommodate customer requirements. In the context of automatic tagging classification and multimodal retrieval, prior…

Obfuscation in privacy engineering denotes a diverse set of data operations aimed at reducing the privacy loss that users incur in by participating in digital systems. Obfuscation's domain of application is vast: privacy-preserving database…

Data is the key factor to drive the development of machine learning (ML) during the past decade. However, high-quality data, in particular labeled data, is often hard and expensive to collect. To leverage large-scale unlabeled data,…

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image…

Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong identity consistency and high prompt diversity presents a…

Today's proliferation of powerful facial recognition systems poses a real threat to personal privacy. As Clearview.ai demonstrated, anyone can canvas the Internet for data and train highly accurate facial recognition models of individuals…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

The growth of the Internet of Things has amplified the need for secure data interactions in cloud-edge ecosystems, where sensitive information is constantly processed across various system layers. Intrusion detection systems are commonly…

Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated to gathering and transferring users' personal interaction data are often underestimated or ignored. Existing…

This work addresses the timely yet underexplored problem of performing inference and finetuning of a proprietary LLM owned by a model provider entity on the confidential/private data of another data owner entity, in a way that ensures the…

Federated learning (FL) is a distributed learning paradigm that allows multiple decentralized clients to collaboratively learn a common model without sharing local data. Although local data is not exposed directly, privacy concerns…

Concealing an object from incoming waves (light and/or sound) remained science fiction for a long time due to the absence of wave-shielding materials in nature. Yet, the invention of artificial materials and new physical principles for…

Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such…

Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factors are shared by only…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…