相关论文: SMS: Self-supervised Model Seeding for Verificatio…

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

Unlearning the data observed during the training of a machine learning (ML) model is an important task that can play a pivotal role in fortifying the privacy and security of ML-based applications. This paper raises the following questions:…

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these…

Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…

Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes. LLMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in…

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…

It is common practice to outsource the training of machine learning models to cloud providers. Clients who do so gain from the cloud's economies of scale, but implicitly assume trust: the server should not deviate from the client's training…

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

A procedure for unfolding the true distribution from experimental data is presented. Machine learning methods are applied for simultaneous identification of an apparatus function and solving of an inverse problem. A priori information about…

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…

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…

SMS messaging is a popular media of communication. Because of its popularity and privacy, it could be used for many illegal purposes. Additionally, since they are part of the day to day life, SMSes can be used as evidence for many legal…