Related papers: Tight Bounds for Machine Unlearning via Differenti…
We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on…
Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to…
The Right to be Forgotten is part of the recently enacted General Data Protection Regulation (GDPR) law that affects any data holder that has data on European Union residents. It gives EU residents the ability to request deletion of their…
Machine unlearning is a process to remove specific data points from a trained model while maintaining the performance on the retain data, addressing privacy or legal requirements. Despite its importance, existing unlearning evaluations tend…
LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…
Differential privacy (DP) provides rigorous privacy guarantees on individual's data while also allowing for accurate statistics to be conducted on the overall, sensitive dataset. To design a private system, first private algorithms must be…
The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize…
With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the removal of their…
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…
Machine unlearning (MU) aims to remove the influence of specific training samples from a well-trained model, a task of growing importance due to the ``right to be forgotten.'' The unlearned model should approach the retrained model, where…
Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…
Federated learning (FL) enables collaborative training of a machine learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy by maintaining data stored locally. Instead of centralizing…
Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation,…
Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties.…
With the passage of the Right to Be Forgotten (RTBF) regulations and the scaling up of language model training datasets, research on model unlearning in large language models (LLMs) has become more crucial. Before the era of LLMs, machine…
As machine learning becomes more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasingly critical requirement. Existing unlearning methods often…
Machine unlearning is an emerging technology that has come to attract widespread attention. A number of factors, including regulations and laws, privacy, and usability concerns, have resulted in this need to allow a trained model to forget…
Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies have explored the effectiveness of unlearning methods on…
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…
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is paramount. Machine…