相关论文: Protecting Privacy Through Approximating Optimal P…

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

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…

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

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…

Large Language models (LLMs) are trained on large amounts of data, which can include sensitive information that may compromise personal privacy. LLMs showed to memorize parts of the training data and emit those data verbatim when an…

Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge…

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

The security of biomedical Multimodal Large Language Models (MLLMs) has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading…

Concerned with privacy threats, memorization in LLMs is often seen as undesirable, specifically for learning. In this paper, we study whether memorization can be avoided when optimally learning a language, and whether the privacy threat…

Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership inference attacks (MIAs) or data extraction attacks, but…

With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although efforts have been made to protect PII in LLMs, existing…

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for…

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…