Related papers: Activation Functions Considered Harmful: Recoverin…

With the mainstream integration of machine learning into security-sensitive domains such as healthcare and finance, concerns about data privacy have intensified. Conventional artificial neural networks (ANNs) have been found vulnerable to…

The decentralized nature of federated learning makes detecting and defending against adversarial attacks a challenging task. This paper focuses on backdoor attacks in the federated learning setting, where the goal of the adversary is to…

Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…

In the realm of deep learning, transformers have emerged as a dominant architecture, particularly in natural language processing tasks. However, with their widespread adoption, concerns regarding the security and privacy of the data…

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Machine learning algorithms based on deep neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy…

Reactive injection attacks are a class of security threats in wireless networks wherein adversaries opportunistically inject spoofing packets in the frequency band of a client thereby forcing the base-station to deploy…

MLaaS Service Providers (SPs) holding a Neural Network would like to keep the Neural Network weights secret. On the other hand, users wish to utilize the SPs' Neural Network for inference without revealing their data. Multi-Party…

Since its debut, SGX has been used in many applications, e.g., secure data processing. However, previous systems usually assume a trusted enclave and ignore the security issues caused by an untrusted enclave. For instance, a vulnerable (or…

Training machine learning models on data from multiple entities without direct data sharing can unlock applications otherwise hindered by business, legal, or ethical constraints. In this work, we design and implement new privacy-preserving…

Application size and complexity are the underlying cause of numerous security vulnerabilities in code. In order to mitigate the risks arising from such vulnerabilities, various techniques have been proposed to isolate the execution of…

Trusted execution environments (TEE) such as Intel's Software Guard Extension (SGX) have been widely studied to boost security and privacy protection for the computation of sensitive data such as human genomics. However, a performance…

Privacy-preserving data release algorithms have gained increasing attention for their ability to protect user privacy while enabling downstream machine learning tasks. However, the utility of current popular algorithms is not always…

We introduce a new timing side-channel attack on Intel CPU processors. Our Frontal attack exploits timing differences that arise from how the CPU frontend fetches and processes instructions while being interrupted. In particular, we observe…

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…

In the effort to learn from extensive collections of distributed data, federated learning has emerged as a promising approach for preserving privacy by using a gradient-sharing mechanism instead of exchanging raw data. However, recent…

Accelerators used for machine learning (ML) inference provide great performance benefits over CPUs. Securing confidential model in inference against off-chip side-channel attacks is critical in harnessing the performance advantage in…

Protected-module architectures (PMAs) have been proposed to provide strong isolation guarantees, even on top of a compromised system. Unfortunately, Intel SGX -- the only publicly available high-end PMA -- has been shown to only provide…