Related papers: Hiding Access-pattern is Not Enough! Veil: A Stora…

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

The cloud computing technique, which was initially used to mitigate the explosive growth of data, has been required to take both data privacy and users' query functionality into consideration. Symmetric searchable encryption (SSE) is a…

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural…

In software development environments, code quality is crucial. This study aims to assist Machine Learning (ML) engineers in enhancing their code by identifying and correcting Data Leakage issues within their models. Data Leakage occurs when…

A statistical cache-aided compression problem with a privacy constraint is studied, where a server has access to a database of $N$ files, $(Y_1,...,Y_N)$, each of size $F$ bits and is linked through a shared channel to $K$ users, where each…

This work proposes a $d$-dimensional quantum multi-secret sharing scheme with a cheat detection mechanism. The dealer creates multiple secrets and distributes the shares of these secrets using multi-access structures and a monotone span…

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

We present MemEC, an erasure-coding-based in-memory key-value (KV) store that achieves high availability and fast recovery while keeping low data redundancy across storage servers. MemEC is specifically designed for workloads dominated by…

Despite increasing advancements in today's information exchange infrastructure, the preservation of user data and privacy still remains a problem. Both insecure baselines and secure solutions leak user data. For example, Certificate…

Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…

Privacy Security of data in Cloud Storage is one of the main issues. Many Frameworks and Technologies are used to preserve data security in cloud storage. [1] Proposes a framework which includes the design of data organization structure,…

The growing gap between data and users calls for innovative tools that address the challenges faced by big data volume, velocity and variety. Along with these standard three V's of big data, an emerging fourth "V" is veracity, which…

Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by developers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval…

Substring-searchable symmetric encryption (substring-SSE) has become increasingly critical for privacy-preserving applications in cloud systems. However, existing schemes remain vulnerable to information leakage during search operations,…

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…

Encryption provides a method to protect data outsourced to a DBMS provider, e.g., in the cloud. However, performing database operations over encrypted data requires specialized encryption schemes that carefully balance security and…

As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools,…

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important…

All data is not equally popular. Often, some portion of data is more frequently accessed than the rest, which causes a skew in popularity of the data items. Adapting to this skew can improve performance, and this topic has been studied…