相关论文: Defending Distributed Classifiers Against Data Poi…

Classification is an important topic in statistics and machine learning with great potential in many real applications. In this paper, we investigate two popular large margin classification methods, Support Vector Machine (SVM) and Distance…

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent years thanks to the progress in deep neural networks and generative modeling. In opposition to old non-parametric methods, new methods use…

We consider distributed on-device learning with limited communication and security requirements. We propose a new robust distributed optimization algorithm with efficient communication and attack tolerance. The proposed algorithm has…

Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing attention. Existing methods either design customized losses…

Support vector machine (SVM) is a popular classifier known for accuracy, flexibility, and robustness. However, its intensive computation has hindered its application to large-scale datasets. In this paper, we propose a new optimal leverage…

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

We propose local distributional smoothness (LDS), a new notion of smoothness for statistical model that can be used as a regularization term to promote the smoothness of the model distribution. We named the LDS based regularization as…

In response to the prevalent concern of TCP SYN flood attacks within the context of Software-Defined Internet of Vehicles (SD-IoV), this study addresses the significant challenge of network security in rapidly evolving vehicular…

Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space;…

The ever-increasing computational demands and deployment costs of large language models (LLMs) have spurred numerous compressing methods. Compared to quantization and unstructured pruning, SVD compression offers superior hardware…

Out-of-Distribution (OOD) detection in semantic segmentation aims to localize anomalous regions at the pixel level, advancing beyond traditional image-level OOD techniques to better suit real-world applications such as autonomous driving.…

Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks,…

Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. We…

This paper proposes a novel Self-Supervised Intrusion Detection (SSID) framework, which enables a fully online Deep Learning (DL) based Intrusion Detection System (IDS) that requires no human intervention or prior off-line learning. The…

Keyword spotting (KWS) refers to the task of identifying a set of predefined words in audio streams. With the advances seen recently with deep neural networks, it has become a popular technology to activate and control small devices, such…

Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during training and has been widely adopted in LLM development, potential…

Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically…

This paper considers distributed optimization algorithms, with application in binary classification via distributed support-vector-machines (D-SVM) over multi-agent networks subject to some link nonlinearities. The agents solve a…