Related papers: Reasoning over Public and Private Data in Retrieva…
When sensitive information is encoded in data, it is important to ensure the privacy of information when attempting to learn useful information from the data. There is a natural tradeoff whereby increasing privacy requirements may decrease…
When individuals are subject to adverse outcomes from machine learning models, providing a recourse path to help achieve a positive outcome is desirable. Recent work has shown that counterfactual explanations - which can be used as a means…
Differential privacy is a rigorous mathematical framework for evaluating and protecting data privacy. In most existing studies, there is a vulnerable assumption that records in a dataset are independent when differential privacy is applied.…
The identity problem today is a data-sharing problem. Today the fixed attributes approach adopted by the consumer identity management industry provides only limited information about an individual, and therefore is of limited value to the…
The rapid integration of generative AI into scientific research has exposed a critical gap in academic disclosure practice. Existing frameworks for reporting AI contributions are uniformly output-oriented -- they document what AI produced,…
Sequential querying of differentially private mechanisms degrades the overall privacy level. In this paper, we answer the fundamental question of characterizing the level of overall privacy degradation as a function of the number of queries…
This paper studies privacy in the context of complex decision support queries composed of multiple conditions on different aggregate statistics combined using disjunction and conjunction operators. Utility requirements for such queries…
The ability to find data is central to the FAIR principles underlying research data stewardship. As with the ability to reuse data, efforts to ensure and enhance findability have historically focused on discoverability of data by other…
Privacy policies are long and complex documents that are difficult for users to read and understand, and yet, they have legal effects on how user data is collected, managed and used. Ideally, we would like to empower users to inform…
Organizations are increasingly interested in allowing external data scientists to explore their sensitive datasets. Due to the popularity of differential privacy, data owners want the data exploration to ensure provable privacy guarantees.…
In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…
Differentially private (DP) machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretraining. While public data assumptions may be reasonable in…
Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving…
The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…
Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the sequence of actions does not require too much effort for…
Context-aware reasoning systems allow drawing sophisticated inferences about users' behaviour and physiological condition, by aggregating data from seemingly unrelated sources. We conducted a general population online survey to evaluate…
Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by…
Personal data has value to both its owner and to institutions who would like to analyze it. Privacy mechanisms protect the owner's data while releasing to analysts noisy versions of aggregate query results. But such strict protections of…
Transparency and reproducibility are often seen in opposition to privacy and confidentiality. Data that need to be kept confidential are seen as an impediment to reproducibility, and privacy would seem to inhibit transparency. I bring a…
Contextual retrieval is a critical technique for today's search engines in terms of facilitating queries and returning relevant information. This paper reports on the development and evaluation of a system designed to tackle some of the…