Related papers: DELTA: Variational Disentangled Learning for Priva…
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)…
Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new…
Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important…
Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…
Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops…
With growing concerns over data privacy, researchers have started using virtual data as an alternative to sensitive real-world images for training person re-identification (Re-ID) models. However, existing virtual datasets produced by game…
Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP…
Data privacy is of great concern in cloud machine-learning service platforms, when sensitive data are exposed to service providers. While private computing environments (e.g., secure enclaves), and cryptographic approaches (e.g.,…
Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted…
Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To…
The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and the cloud to reduce latency and protect user privacy.…
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…
Federated Learning (FL) has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant…
Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…
Federated Unlearning (FUL) focuses on client data and computing power to offer a privacy-preserving solution. However, high computational demands, complex incentive mechanisms, and disparities in client-side computing power often lead to…
Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need…
Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training…