Related papers: AVEC: Bootstrapping Privacy for Local LLMs

The existing variants of the Differential Evolution (DE) algorithm come with certain limitations, such as poor local search and susceptibility to premature convergence. This study introduces Adaptive Differential Evolution with…

Graph embedding has become a powerful tool for learning latent representations of nodes in a graph. Despite its superior performance in various graph-based machine learning tasks, serious privacy concerns arise when the graph data contains…

Attribute-driven privacy aims to conceal a single user's attribute, contrary to anonymisation that tries to hide the full identity of the user in some data. When the attribute to protect from malicious inferences is binary, perfect privacy…

Inference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets…

As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillance raises significant concerns regarding visual recording and…

While machine learning has proven to be a powerful data-driven solution to many real-life problems, its use in sensitive domains has been limited due to privacy concerns. A popular approach known as **differential privacy** offers provable…

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery. We introduce…

Conformal prediction (CP) provides sets of candidate classes with a guaranteed probability of containing the true class. However, it typically relies on a calibration set with clean labels. We address privacy-sensitive scenarios where the…

Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which…

The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the learned latent…

In hierarchical cognitive radio networks, edge or cloud servers utilize the data collected by edge devices for modulation classification, which, however, is faced with problems of the computation load, transmission overhead, and data…

E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs…

Federated learning enables machine learning algorithms to be trained over a network of multiple decentralized edge devices without requiring the exchange of local datasets. Successfully deploying federated learning requires ensuring that…

Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the system should retain strong offensive capability inside an…

Edge computing facilitates deep learning in resource-constrained environments, but challenges such as resource heterogeneity and dynamic constraints persist. This paper introduces AMP4EC, an Adaptive Model Partitioning framework designed to…

In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness).…

Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy…

As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness value of information flows in responses from LLMs. A…