Related papers: Real-world Edge Neural Network Implementations Lea…
Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and memory constraints…
Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…
Surface electromyography (EMG) enables non-invasive human-computer interaction in rehabilitation, prosthetics, and virtual reality. While deep learning models achieve over 97% classification accuracy, their vulnerability to adversarial…
Speech emotion recognition (SER) is constantly gaining attention in recent years due to its potential applications in diverse fields and thanks to the possibility offered by deep learning technologies. However, recent studies have shown…
Federated learning enables multiple users to build a joint model by sharing their model updates (gradients), while their raw data remains local on their devices. In contrast to the common belief that this provides privacy benefits, we here…
Differential privacy quantifies privacy through the privacy budget $\epsilon$, yet its practical interpretation is complicated by variations across models and datasets. Recent research on differentially private machine learning and…
Wearable data serves various health monitoring purposes, such as determining activity states based on user behavior and providing tailored exercise recommendations. However, the individual data perception and computational capabilities of…
This paper presents SNOW-SCA, the first power side-channel analysis (SCA) attack of a 5G mobile communication security standard candidate, SNOW-V, running on a 32-bit ARM Cortex-M4 microcontroller. First, we perform a generic known-key…
Power side-channel attacks exploit the dynamic power consumption of cryptographic operations to leak sensitive information of encryption hardware. Therefore, it is necessary to conduct power side-channel analysis for assessing the…
DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model…
The massive trend toward embedded systems introduces new security threats to prevent. Malicious firmware makes it easier to launch cyberattacks against embedded systems. Systems infected with malicious firmware maintain the appearance of…
While machine learning (ML) models are becoming mainstream, especially in sensitive application areas, the risk of data leakage has become a growing concern. Attacks like membership inference (MIA) have shown that trained models can reveal…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
We introduce IMPACT, a set of high-throughput main memory-based timing attacks that leverage characteristics of processing-in-memory (PiM) architectures to establish covert and side channels. IMPACT enables high-throughput communication and…
Trusted Execution Environments (TEEs) have been proposed as a solution to protect code confidentiality in scenarios where computation is outsourced to an untrusted operator. We study the resilience of such solutions to side-channel attacks…
MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on their data. However, ensuring user input privacy and secure…
Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…
Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. While fine-tuning enhances performance by internalizing domain…
Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) is a direct communication pathway between the human brain and a computer. Most research so far studied more accurate BCIs, but much less attention has been paid…
In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, under mild assumptions on the data, provably achieves…