Related papers: DSperse: A Framework for Targeted Verification in …

Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning performance by leveraging unlabeled data when labels are insufficient. Recently, SSL with deep models has proven to be successful on standard…

Sparse sensor array selection arises in many engineering applications, where it is imperative to obtain maximum spatial resolution from a limited number of array elements. Recent research shows that computational complexity of array…

As the demand for machine learning-based inference increases in tandem with concerns about privacy, there is a growing recognition of the need for secure machine learning, in which secret models can be used to classify private data without…

Growing data privacy demands, driven by regulations like GDPR and CCPA, require machine unlearning methods capable of swiftly removing the influence of specific training points. Although verified approaches like SISA, using data slicing and…

We consider the problem of maintaining sparsity in private distributed storage of confidential machine learning data. In many applications, e.g., face recognition, the data used in machine learning algorithms is represented by sparse…

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…

Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…

Context: The IoT system infrastructure platform facility vulnerability attack has become the main battlefield of network security attacks. Most of the traditional vulnerability mining methods rely on vulnerability detection tools to realize…

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…

Disaggregated memory is an upcoming data center technology that will allow nodes (servers) to share data efficiently. Sharing data creates a debate on the level of cache coherence the system should provide. While current proposals aim to…

Pruning neural networks has proven to be a successful approach to increase the efficiency and reduce the memory storage of deep learning models without compromising performance. Previous literature has shown that it is possible to achieve a…

Semi-supervised learning (SSL) provides an effective means of leveraging unlabelled data to improve a model performance. Even though the domain has received a considerable amount of attention in the past years, most methods present the…

Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…

Distribution Service (DDS) is a realtime peer-to-peer protocol that serves as a scalable middleware between distributed networked systems found in many Industrial IoT domains such as automotive, medical, energy, and defense. Since the…

Conformal prediction is a distribution-free framework for uncertainty quantification that replaces point predictions with sets, offering marginal coverage guarantees (i.e., ensuring that the prediction sets contain the true label with a…

Currently, progressively larger deep neural networks are trained on ever growing data corpora. As this trend is only going to increase in the future, distributed training schemes are becoming increasingly relevant. A major issue in…

FPGAs have been shown to be a promising platform for deploying Quantised Neural Networks (QNNs) with high-speed, low-latency, and energy-efficient inference. However, the complexity of modern deep-learning models limits the performance on…