Related papers: Full-privacy secured search engine empowered by ef…

Computing technologies pervade physical spaces and human lives, and produce a vast amount of data that is available for analysis. However, there is a growing concern that potentially sensitive data may become public if the collected data…

Threshold fully homomorphic encryption (ThFHE) enables multiple parties to compute functions over their sensitive data without leaking data privacy. Most of existing ThFHE schemes are restricted to full threshold and require the…

Recent studies have raised concerns about the potential threats large language models (LLMs) pose to academic integrity and copyright protection. Yet, their investigation is predominantly focused on literal copies of original texts. Also,…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

The rapid development of artificial intelligence has brought considerable convenience, yet also introduces significant security risks. One of the research hotspots is to balance data privacy and utility in the real world of artificial…

Cloud computing is emerging as a revolutionary computing paradigm, while security and privacy become major concerns in the cloud scenario. For which Searchable Encryption (SE) technology is proposed to support efficient retrieval of…

Programmers currently enjoy access to a very high number of code repositories and libraries of ever increasing size. The ensuing potential for reuse is however hampered by the fact that searching within all this code becomes an increasingly…

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes…

Acronyms and long-forms are commonly found in research documents, more so in documents from scientific and legal domains. Many acronyms used in such documents are domain-specific and are very rarely found in normal text corpora. Owing to…

While the flexible capabilities of large language models (LLMs) allow them to answer a range of queries based on existing learned knowledge, information retrieval to augment generation is an important tool to allow LLMs to answer questions…

The ongoing Big Data explosion has created a demand for efficient and scalable algorithms for similarity search. Most recent work has focused on \textit{approximate} $k$-NN search, and while this may be sufficient for some applications,…

Searchable encryption (SE) is one of the key enablers for building encrypted databases. It allows a cloud server to search over encrypted data without decryption. Dynamic SE additionally includes data addition and deletion operations to…

Today, large amounts of valuable data are distributed among millions of user-held devices, such as personal computers, phones, or Internet-of-things devices. Many companies collect such data with the goal of using it for training machine…

Query-by-example (QbE) speech search is the task of matching spoken queries to utterances within a search collection. In low- or zero-resource settings, QbE search is often addressed with approaches based on dynamic time warping (DTW).…

In this work, we propose a differentially private algorithm for publishing matrices aggregated from sparse vectors. These matrices include social network adjacency matrices, user-item interaction matrices in recommendation systems, and…

Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy concerns for both data owners and users. Privacy-preserving RAG systems address these concerns by…

Despite our best efforts, deep learning models remain highly vulnerable to even tiny adversarial perturbations applied to the inputs. The ability to extract information from solely the output of a machine learning model to craft adversarial…

In a Public Safety (PS) situation, agents may require critical and personally identifiable information. Therefore, not only does context and location-aware information need to be available, but also the privacy of such information should be…

Information Disguise (ID), a part of computational ethics in Natural Language Processing (NLP), is concerned with best practices of textual paraphrasing to prevent the non-consensual use of authors' posts on the Internet. Research on ID…

Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform…