相关论文: Matryoshka: Stealing Functionality of Private ML D…

Steganalysis is a collection of techniques used to detect whether secret information is embedded in a carrier using steganography. Most of the existing steganalytic methods are based on machine learning, which typically requires training a…

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…

The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narrow linguistic focus that neglects most of the world's…

Steganography is the task of concealing a message within a medium such that the presence of the hidden message cannot be detected. Beyond the standard scope of private-key steganography, steganography is also potentially interesting from…

Steganography is the art of hiding a secret message inside a publicly visible carrier message. Ideally, it is done without modifying the carrier, and with minimal loss of information in the secret message. Recently, various deep learning…

State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…

The current approach of information hiding based on deep learning model can not directly use the original data as carriers, which means the approach can not make use of the existing data in big data to hiding information. We proposed a…

Data hiding is the art of hiding secret data into a cover object such as digital image for covert communication. In this paper, we make the first step towards hiding ``data hiding'', which is totally different from many conventional works…

Deep learning has achieved incredible success over the past years, especially in various challenging predictive spatio-temporal analytics (PSTA) tasks, such as disease prediction, climate forecast, and traffic prediction, where intrinsic…

Deep learning model developers often use cloud GPU resources to experiment with large data and models that need expensive setups. However, this practice raises privacy concerns. Adversaries may be interested in: 1) personally identifiable…

Pathology foundation models (FMs) have driven significant progress in computational pathology. However, these high-performing models can easily exceed a billion parameters and produce high-dimensional embeddings, thus limiting their…

2D Matryoshka training enables a single embedding model to generate sub-network representations across different layers and embedding dimensions, offering adaptability to diverse computational and task constraints. However, its…

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

Embeddings from Large Language Models (LLMs) have emerged as critical components in various applications, particularly for information retrieval. While high-dimensional embeddings generally demonstrate superior performance as they contain…

Despite the impressive generative abilities of black-box large language models (LLMs), their inherent opacity hinders further advancements in capabilities such as reasoning, planning, and personalization. Existing works aim to enhance LLM…

Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typically involves two parties: the model developers and…

The deployment of deep learning applications has to address the growing privacy concerns when using private and sensitive data for training. A conventional deep learning model is prone to privacy attacks that can recover the sensitive…

Federated Learning (FL) solutions with central Differential Privacy (DP) have seen large improvements in their utility in recent years arising from the matrix mechanism, while FL solutions with distributed (more private) DP have lagged…

In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all…

Large language models (LLMs) have emerged as powerful knowledge bases yet are limited by static training data, leading to issues such as hallucinations and safety risks. Editing a model's internal knowledge through the locate-and-edit…