Related papers: SecPE: Secure Prompt Ensembling for Private and Ro…
Hardware-enclaves that target complex CPU designs compromise both security and performance. Programs have little control over micro-architecture, which leads to side-channel leaks, and then have to be transformed to have worst-case control-…
Federated Learning enables one to jointly train a machine learning model across distributed clients holding sensitive datasets. In real-world settings, this approach is hindered by expensive communication and privacy concerns. Both of these…
While machine learning has become pervasive in as diversified fields as industry, healthcare, social networks, privacy concerns regarding the training data have gained a critical importance. In settings where several parties wish to…
As the demand for machine learning-based inference increases in tandem with concerns about privacy, there is a growing recognition of the need for secure machine learning, in which secret models can be used to classify private data without…
Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the…
Secure aggregation protocols ensure the privacy of users' data in federated learning by preventing the disclosure of local gradients. Many existing protocols impose significant communication and computational burdens on participants and may…
Private large language model (LLM) inference based on cryptographic primitives offers a promising path towards privacy-preserving deep learning. However, existing frameworks only support dense LLMs like LLaMA-1 and struggle to scale to…
System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…
Machine Learning (ML) has become one of the most impactful fields of data science in recent years. However, a significant concern with ML is its privacy risks due to rising attacks against ML models. Privacy-Preserving Machine Learning…
Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM…
Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference…
The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…
As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat…
Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches typically separate the optimization of prompt instructions…
Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…
After large models (LMs) have gained widespread acceptance in code-related tasks, their superior generative capacity has greatly promoted the application of the code LM. Nevertheless, the security of the generated code has raised attention…
With the rapid advancement of AI technology, we have seen more and more concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial…
Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods require extensive epochs to achieve convergence, a demand…
We consider a collaborative learning scenario in which multiple data-owners wish to jointly train a logistic regression model, while keeping their individual datasets private from the other parties. We propose COPML, a fully-decentralized…
Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…