Related papers: Safety and Performance, Why not Both? Bi-Objective…

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Machine learning models require datasets for effective training, but directly sharing raw data poses significant privacy risk such as membership inference attacks (MIA). To mitigate the risk, privacy-preserving techniques such as data…

The rapid growth of large models' size has far outpaced that of computing resources. To bridge this gap, encouraged by the parsimonious relationship between genotype and phenotype in the brain's growth and development, we propose the…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.…

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including…

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…

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has become essential, especially for privacy-sensitive applications. Membership Inference Attacks…

Intrusion detection is a long standing and crucial problem in security. A system capable of detecting intrusions automatically is on great demand in enterprise security solutions. Existing solutions rely heavily on hand-crafted rules…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Increasingly, model compression techniques enable large language models (LLMs) to be deployed in real-world applications. As a result of this momentum towards local deployment, compressed LLMs will interact with a large population. Prior…

The predictive advantage of combining several different predictive models is widely accepted. Particularly in time series forecasting problems, this combination is often dynamic to cope with potential non-stationary sources of variation…

This paper explores the role and challenges of Artificial Intelligence (AI) algorithms, specifically AI-based software elements, in autonomous driving systems. These AI systems are fundamental in executing real-time critical functions in…

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

The recent advances in machine learning and deep neural networks have made them attractive candidates for wireless communications functions such as channel estimation, decoding, and downlink channel state information (CSI) compression.…