Related papers: Randomization Techniques to Mitigate the Risk of C…
The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In…
With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unlearning methods often assume access to the complete training…
Today, the publication of microdata poses a privacy threat. Vast research has striven to define the privacy condition that microdata should satisfy before it is released, and devise algorithms to anonymize the data so as to achieve this…
Language models may memorize more than just facts, including entire chunks of texts seen during training. Fair use exemptions to copyright laws typically allow for limited use of copyrighted material without permission from the copyright…
It is well-known that many machine learning models are susceptible to adversarial attacks, in which an attacker evades a classifier by making small perturbations to inputs. This paper discusses how industrial copyright detection tools,…
Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…
We propose an unsupervised solution to the Authorship Verification task that utilizes pre-trained deep language models to compute a new metric called DV-Distance. The proposed metric is a measure of the difference between the two authors…
Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…
Differential privacy (DP) provides a robust model to achieve privacy guarantees for released information. We examine the protection potency of sanitized multi-dimensional frequency distributions via DP randomization mechanisms against…
We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs. We consider the scenario where a…
Process mining employs event data extracted from different types of information systems to discover and analyze actual processes. Event data often contain highly sensitive information about the people who carry out activities or the people…
Approximate circuits often achieve exceptional trade-offs between computational accuracy and hardware efficiency, making them attractive for deployment as reusable Intellectual Property (IP) cores. However, safeguarding such circuits…
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore,…
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…
Recently introduced privacy legislation has aimed to restrict and control the amount of personal data published by companies and shared to third parties. Much of this real data is not only sensitive requiring anonymization, but also…
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…
Genome-wide association studies (GWAS) are an essential tool in biomedical research for identifying genetic factors linked to health and disease. However, publicly releasing GWAS summary statistics poses well-recognized privacy risks,…
Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…
Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy guarantee is an error-prone process, both in designing…