Related papers: Plinius: Secure and Persistent Machine Learning Mo…

This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami…

The massive deployment of Machine Learning (ML) models raises serious concerns about data protection. Privacy-enhancing technologies (PETs) offer a promising first step, but hard challenges persist in achieving confidentiality and…

Generating up to date, well labeled datasets for machine learning (ML) security models is a unique engineering challenge, as large data volumes, complexity of labeling, and constant concept drift makes it difficult to generate effective…

Large language models (LLMs) have recently revolutionized language processing tasks but have also brought ethical and legal issues. LLMs have a tendency to memorize potentially private or copyrighted information present in the training…

Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key…

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

The growing reliance on artificial intelligence (AI) in customer support has significantly improved operational efficiency and user experience. However, traditional machine learning (ML) approaches, which require extensive local training on…

Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of…

When training large machine learning models with many variables or parameters, a single machine is often inadequate since the model may be too large to fit in memory, while training can take a long time even with stochastic updates. A…

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

Trusted Execution Environments (TEEs), such as Intel Software Guard eXtensions (SGX), are considered as a promising approach to resolve security challenges in clouds. TEEs protect the confidentiality and integrity of application code and…

Cloud providers are extending support for trusted hardware primitives such as Intel SGX. Simultaneously, the field of deep learning is seeing enormous innovation as well as an increase in adoption. In this paper, we ask a timely question:…

The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive training datasets. Recent studies have demonstrated that an…

With the advent of big data era and the development of artificial intelligence and other technologies, data security and privacy protection have become more important. Recommendation systems have many applications in our society, but the…

Continual pre-training has demonstrated significant potential in enhancing model performance, particularly in domain-specific scenarios. The most common approach for packing data before continual pre-training involves concatenating input…

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…

We present a five-module pedagogical framework for teaching physics-informed machine learning (ML) through two progressively complex physical systems: a driven, damped nonlinear pendulum and a one-dimensional quantum anharmonic oscillator.…

By replacing standard non-linearities with polynomial activations, Polynomial Neural Networks (PNNs) are pivotal for applications such as privacy-preserving inference via Homomorphic Encryption (HE). However, training PNNs effectively…