Related papers: Sentence-level Privacy for Document Embeddings
Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…
We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…
Differential Privacy (DP) has emerged as a pivotal approach for safeguarding individual privacy in data analysis, yet its practical adoption is often hindered by challenges in the implementation and communication of DP. This paper presents…
Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective…
Context: As mobile applications (Apps) widely spread over our society and life, various personal information is constantly demanded by Apps in exchange for more intelligent and customized functionality. An increasing number of users are…
The field of text privatization often leverages the notion of $\textit{Differential Privacy}$ (DP) to provide formal guarantees in the rewriting or obfuscation of sensitive textual data. A common and nearly ubiquitous form of DP application…
Local differential privacy (LPD) is a distributed variant of differential privacy (DP) in which the obfuscation of the sensitive information is done at the level of the individual records, and in general it is used to sanitize data that are…
Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…
The study of Differential Privacy (DP) in Natural Language Processing often views the task of text privatization as a $\textit{rewriting}$ task, in which sensitive input texts are rewritten to hide explicit or implicit private information.…
Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…
Differential Privacy (DP) for text has recently taken the form of text paraphrasing using language models and temperature sampling to better balance privacy and utility. However, the geometric distortion of DP regarding the structure and…
Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source. However, its application to image data has long been considered impractical due to the…
The use of language models as remote services requires transmitting private information to external providers, raising significant privacy concerns. This process not only risks exposing sensitive data to untrusted service providers but also…
Automatically mining sentiment tendency contained in natural language is a fundamental research to some artificial intelligent applications, where solutions alternate with challenges. Transfer learning and multi-task learning techniques…
Differential privacy (DP) has established itself as one of the standards for ensuring privacy of individual data. However, reasoning about DP is a challenging and error-prone task, hence methods for formal verification and refutation of DP…
High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated data will soon have been used. Additionally, publicly…
We initiate the study of distribution testing under \emph{user-level} local differential privacy, where each of $n$ users contributes $m$ samples from the unknown underlying distribution. This setting, albeit very natural, is significantly…
Mobile apps and location-based services generate large amounts of location data that can benefit research on traffic optimization, context-aware notifications and public health (e.g., spread of contagious diseases). To preserve individual…
Sentence and word embeddings encode structural and semantic information in a distributed manner. Part of the information encoded -- particularly lexical information -- can be seen as continuous, whereas other -- like structural information…
Large language models (LLMs) frequently memorize sensitive or personal information, raising significant privacy concerns. Existing variants of differential privacy stochastic gradient descent (DPSGD) inject uniform noise into every gradient…