相关论文: A User Model for Information Erasure

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records. We…

Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…

HTTP client hints are a set of standardized HTTP request headers designed to modernize and potentially replace the traditional user agent string. While the user agent string exposes a wide range of information about the client's browser and…

Information or data is very crucial resource to us. Thus securing the information becomes all the more necessary. The communication media through which we send data does not provide data security, so other methods of securing data are…

Analyzing interaction data provides an opportunity to learn about users, uncover their underlying goals, and create intelligent visualization systems. The first step for intelligent response in visualizations is to enable computers to infer…

Data hiding is the art of hiding secret data into a cover object such as digital image for covert communication. In this paper, we make the first step towards hiding ``data hiding'', which is totally different from many conventional works…

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Purveyors of malicious network attacks continue to increase the complexity and the sophistication of their techniques, and their ability to evade detection continues to improve as well. Hence, intrusion detection systems must also evolve to…

Usability is a key quality attribute of successful software systems. Unfortunately, there is no common understanding of the factors influencing usability and their interrelations. Hence, the lack of a comprehensive basis for designing,…

A Proof of Secure Erasure (PoSE) is a communication protocol where a verifier seeks evidence that a prover has erased its memory within the time frame of the protocol execution. Designers of PoSE protocols have long been aware that, if a…

The article explores the cultural shift from recording to deleting information in the digital age and its implications on privacy, intellectual property (IP), and Large Language Models like ChatGPT. It begins by defining a delete culture…

Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to be forgotten} that mandates industry applications to remove…

Recently, the enactment of privacy regulations has promoted the rise of the machine unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise unlearning, such that a learnt model will not expose user's privacy…

Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising…

We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be…

Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…

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…

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

The exchange of personal information in digital environments poses significant risks, including identity theft, privacy breaches, and data misuse. Addressing these challenges requires a deep understanding of user behavior and mental models…

In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model.…