Related papers: Privatization-Safe Transactional Memories (Extende…
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…
Training with differential privacy (DP) provides a guarantee to members in a dataset that they cannot be identified by users of the released model. However, those data providers, and, in general, the public, lack methods to efficiently…
Oblivious RAM simulation is a method for achieving confidentiality and privacy in cloud computing environments. It involves obscuring the access patterns to a remote storage so that the manager of that storage cannot infer information about…
We investigate the application of large language models (LLMs), specifically GPT-4, to scenarios involving the tradeoff between privacy and utility in tabular data. Our approach entails prompting GPT-4 by transforming tabular data points…
Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high barrier for non-expert practitioners. Prior works either rely…
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…
It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with reasonable accuracy. To address this issue, we propose a novel…
Security bugs and trapdoors in smart contracts have been impacting the Ethereum community since its inception. Conceptually, the 1.45-million Ethereum's contracts form a single "gigantic program" whose behaviors are determined by the…
Transactions can simplify distributed applications by hiding data distribution, concurrency, and failures from the application developer. Ideally the developer would see the abstraction of a single large machine that runs transactions…
We show how oracles which only allow for classical query access can be used to construct a variety of quantum cryptographic primitives which do not require long-term quantum memory or global entanglement. Specifically, if a quantum party…
Reasoning about hyperproperties of concurrent implementations, such as the guarantees these implementations provide to randomized client programs, has been a long-standing challenge. Standard linearizability enables the use of atomic…
Local differential privacy has recently surfaced as a strong measure of privacy in contexts where personal information remains private even from data analysts. Working in a setting where both the data providers and data analysts want to…
In this work, we investigate if statistical privacy can enhance the performance of ORAM mechanisms while providing rigorous privacy guarantees. We propose a formal and rigorous framework for developing ORAM protocols with statistical…
Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many…
Differential privacy is a formal, mathematical definition of data privacy that has gained traction in academia, industry, and government. The task of correctly constructing differentially private algorithms is non-trivial, and mistakes have…
Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…
Federated Learning (FL) solutions with central Differential Privacy (DP) have seen large improvements in their utility in recent years arising from the matrix mechanism, while FL solutions with distributed (more private) DP have lagged…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…