相关论文: Planting and Mitigating Memorized Content in Predi…

Large language models, trained on massive corpora, are prone to verbatim memorization of training data, creating significant privacy and copyright risks. While previous works have proposed various definitions for memorization, many exhibit…

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…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing and reasoning over diverse modalities, but their advanced abilities also raise significant privacy concerns, particularly regarding Personally…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural…

Large language models specialized for code (CodeLLMs) have demonstrated remarkable capabilities in generating code snippets, documentation, and test cases. However, despite their promising capabilities, CodeLLMs can inadvertently memorize…

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this…

As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from crawlers or model developers, fundamentally limiting their…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new practical data extraction attack that we call "neural…

Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…

Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on…

Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly involving personally identifiable information (PII).…

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…