Related papers: Provably Protecting Fine-Tuned LLMs from Training …

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying differential privacy (DP), a canonical notion with provable privacy guarantees for machine…

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety alignment, e.g., by greatly increasing susceptibility 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…

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient…

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

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…

Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant…

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…