Related papers: What's a little leakage between friends?

Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…

Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…

Information leakage to a guessing adversary in index coding is studied, where some messages in the system are sensitive and others are not. The non-sensitive messages can be used by the server like secret keys to mitigate leakage of the…

Underground forums where users discuss, buy, and sell illicit services and goods facilitate a better understanding of the economy and organization of cybercriminals. Prior work has shown that in particular private interactions provide a…

In multi-agent planning, agents jointly compute a plan that achieves mutual goals, keeping certain information private to the individual agents. Agents' coordination is achieved through the transmission of messages. These messages can be a…

Social Media Site (SMS) usage has grown rapidly in the last few years. This sudden increase in SMS usage creates an opportunity for data leakage which could compromise personal and/or professional life. In this work, we have reviewed…

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…

Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use…

A novel private communication framework is proposed where privacy is induced by transmitting over a channel instances of linear inverse problems that are identifiable to the legitimate receiver but unidentifiable to an eavesdropper. The gap…

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

Messaging systems built on mesh networks consisting of smartphones communicating over Bluetooth have been used by protesters around the world after governments have disrupted Internet connectivity. Unfortunately, existing systems have been…

Social chatbots, also known as chit-chat chatbots, evolve rapidly with large pretrained language models. Despite the huge progress, privacy concerns have arisen recently: training data of large language models can be extracted via model…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

An information theoretic privacy mechanism design problem for two scenarios is studied where the private data is either hidden or observable. In each scenario, privacy leakage constraints are considered using two different measures. In…

Online social networks are used frequently by many people: Staying in contact with friends and sharing experiences with them is very important. However, users are increasingly concerned that their data will end up in the hands of strangers…

Harnessing a block-sparse prior to recover signals through underdetermined linear measurements has been extensively shown to allow exact recovery in conditions where classical compressed sensing would provably fail. We exploit this result…

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

The ubiquity of mobile devices has led to the proliferation of mobile services that provide personalized and context-aware content to their users. Modern mobile services are distributed between end-devices, such as smartphones, and remote…

The exponential growth of data collection necessitates robust privacy protections that preserve data utility. We address information disclosure against adversaries with bounded prior knowledge, modeled by an entropy constraint $H(X) \geq…