相关论文: A Decentralized Spike-based Learning Framework for…

Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address this limitation, we shift the defensive paradigm toward a novel active,…

The rise in embedded and IoT device usage comes with an increase in LTE usage as well. About 70\% of an estimated 18 billion IoT devices will be using cellular LTE networks for efficient connections. This introduces several challenges such…

Efficient adversarial attack methods are critical for assessing the robustness of computer vision models. In this paper, we reconstruct the optimization objective for generating adversarial examples as "maximizing the difference between the…

Semi-supervised learning (SSL) aims to help reduce the cost of the manual labelling process by leveraging a substantial pool of unlabelled data alongside a limited set of labelled data during the training phase. Since pixel-level manual…

In this paper, the problem of federated learning (FL) through digital communication between clients and a parameter server (PS) over a multiple access channel (MAC), also subject to differential privacy (DP) constraints, is studied. More…

Domain Specific Languages (DSLs) increase programmer productivity and provide high performance. Their targeted abstractions allow scientists to express problems at a high level, providing rich details that optimizing compilers can exploit…

Bidirectional privacy-preservation federated learning is crucial as both local gradients and the global model may leak privacy. However, only a few works attempt to achieve it, and they often face challenges such as excessive communication…

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions,…

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Safe Reinforcement Learning (SafeRL) is the subfield of reinforcement learning that explicitly deals with safety constraints during the learning and deployment of agents. This survey provides a mathematically rigorous overview of SafeRL…

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications. Previous studies addressed these…

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…

In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design…

Self-Supervised Learning (SSL) has emerged as a significant paradigm in representation learning thanks to its ability to learn without extensive labeled data, its strong generalization capabilities, and its potential for privacy…

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

Metric Differential Privacy (mDP) extends the concept of Differential Privacy (DP) to serve as a new paradigm of data perturbation. It is designed to protect secret data represented in general metric space, such as text data encoded as word…

What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed? To provide a concrete answer to this question, this paper unifies two major learning frameworks:…

The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level…

Federated learning (FL) and split learning (SL) are the two popular distributed machine learning (ML) approaches that provide some data privacy protection mechanisms. In the time-series classification problem, many researchers typically use…