相关论文: Connecting the Dots: Privacy Leakage via Write-Acc…

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest or news feed. State-of-the-art recommendation models rely on…

Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality and performance of an LLM application highly depend on its…

The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

In this paper we address the problem of large space consumption for protocols in the Bounded Retrieval Model (BRM), which require users to store large secret keys subject to adversarial leakage. We propose a method to derive keys for such…

Data publishing under privacy constraints can be achieved with mechanisms that add randomness to data points when released to an untrusted party, thereby decreasing the data's utility. In this paper, we analyze this privacy-utility tradeoff…

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but…

Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

In heterogeneous SoCs, accelerators like integrated GPUs (iGPUs) are integrated on the same chip as CPUs, sharing the memory subsystem. In such systems, the massive memory requests from throughput-oriented accelerators significantly…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

Adversaries with physical access to a target platform can perform cold boot or DMA attacks to extract sensitive data from the RAM. In response, several main-memory encryption schemes have been proposed to prevent such attacks. Also hardware…

With the rapid adoption of Federated Learning (FL) as the training and tuning protocol for applications utilizing Large Language Models (LLMs), recent research highlights the need for significant modifications to FL to accommodate the…

As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…

Information leakage to a guessing adversary in index coding is studied, where some messages in the system are sensitive and others are not. The non-sensitive messages can be used by the server like secret keys to mitigate leakage of the…