Related papers: Distributed Transition System with Tags and Value-…
Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents. In the big data era, performing inference within the distributed and federated learning (DL and FL)…
Model Inversion (MI) attacks, which reconstruct the training dataset of neural networks, pose significant privacy concerns in machine learning. Recent MI attacks have managed to reconstruct realistic label-level private data, such as the…
Absolute anonymization, conceived as an irreversible transformation that prevents re-identification and sensitive value disclosure, has proven to be a broken promise. Consequently, modern data protection must shift toward a privacy-utility…
Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…
Data sharing enables critical advances in many research areas and business applications, but it may lead to inadvertent disclosure of sensitive summary statistics (e.g., means or quantiles). Existing literature only focuses on protecting a…
Research on differentially private synthetic tabular data has largely focused on independent and identically distributed rows where each record corresponds to a unique individual. This perspective neglects the temporal complexity in…
Differential privacy (DP) has been accepted as a rigorous criterion for measuring the privacy protection offered by random mechanisms used to obtain statistics or, as we will study here, synthetic datasets from confidential data. Methods to…
Sharing trajectories is beneficial for many real-world applications, such as managing disease spread through contact tracing and tailoring public services to a population's travel patterns. However, public concern over privacy and data…
The Shapley value has been proposed as a solution to many applications in machine learning, including for equitable valuation of data. Shapley values are computationally expensive and involve the entire dataset. The query for a point's…
Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization…
E-values have gained prominence as flexible tools for statistical inference and risk control, enabling anytime- and post-hoc-valid procedures under minimal assumptions. However, many real-world applications fundamentally rely on sensitive…
Recently, Directed Acyclic Graph (DAG) based Distributed Ledgers have been proposed for various applications in the smart mobility domain [1]. While many application studies have been described in the literature, an open problem in the DLT…
Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…
The Internet of Things (IoT) and Distributed ledger technology (DLT) have significantly changed our daily lives. Due to their distributed operational environment and naturally decentralized applications, the convergence of these two…
Discrete Diffusion Large Language Models (dLLMs) have recently emerged as a competitive paradigm for non-autoregressive language modeling. Their distinctive decoding mechanism enables faster inference speed and strong performance in code…
Location-Based Services (LBSs) offer significant convenience to mobile users but pose significant privacy risks, as attackers can infer sensitive personal information through spatiotemporal correlations in user trajectories. Since users'…
In recent years, traditional cybersecurity safeguards have proven ineffective against insider threats. Famous cases of sensitive information leaks caused by insiders, including the WikiLeaks release of diplomatic cables and the Edward…
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…
In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves…