Related papers: Obfuscation for Privacy-preserving Syntactic Parsi…
Modern search engines extensively personalize results by building detailed user profiles based on query history and behaviour. While personalization can enhance relevance, it introduces privacy risks and can lead to filter bubbles. This…
Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural network to operate on…
Authorship obfuscation aims to disguise the identity of an author within a text by altering the writing style, vocabulary, syntax, and other linguistic features associated with the text author. This alteration needs to balance privacy and…
Data obfuscation deals with the problem of masking a data-set in such a way that the utility of the data is maximized while minimizing the risk of the disclosure of sensitive information. To protect data we address some ways that may as…
Fully homomorphic encryption has allowed devices to outsource computation to third parties while preserving the secrecy of the data being computed on. Many images contain sensitive information and are commonly sent to cloud services to…
Word obfuscation or substitution means replacing one word with another word in a sentence to conceal the textual content or communication. Word obfuscation is used in adversarial communication by terrorist or criminals for conveying their…
Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new…
As more and more pre-trained language models adopt on-cloud deployment, the privacy issues grow quickly, mainly for the exposure of plain-text user data (e.g., search history, medical record, bank account). Privacy-preserving inference of…
Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of…
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…
Language Models as a Service (LMaaS) offers convenient access for developers and researchers to perform inference using pre-trained language models. Nonetheless, the input data and the inference results containing private information are…
With the fast development of natural language processing, recent advances in information hiding focus on covertly embedding secret information into texts. These algorithms either modify a given cover text or directly generate a text…
The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission…
Preserving privacy is an undeniable benefit to users online. However, this benefit (unfortunately) also extends to those who conduct cyber attacks and other types of malfeasance. In this work, we consider the scenario in which Privacy…
The problem of obfuscating the authorship of a text document has received little attention in the literature to date. Current approaches are ad-hoc and rely on assumptions about an adversary's auxiliary knowledge which makes it difficult to…
Differential privacy provides the first theoretical foundation with provable privacy guarantee against adversaries with arbitrary prior knowledge. The main idea to achieve differential privacy is to inject random noise into statistical…
Cryptography and data science research grew exponential with the internet boom. Legacy encryption techniques force users to make a trade-off between usability, convenience, and security. Encryption makes valuable data inaccessible, as it…
Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate…
The main aim of Privacy-Preserving Machine Learning (PPML) is to protect the privacy and provide security to the data used in building Machine Learning models. There are various techniques in PPML such as Secure Multi-Party Computation,…
Feature selection is a technique that extracts a meaningful subset from a set of features in training data. When the training data is large-scale, appropriate feature selection enables the removal of redundant features, which can improve…