Related papers: On Active Privacy Auditing in Supervised Fine-tuni…

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthcare. However, the…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. Recent studies have reported that MIAs perform only…

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…

Large Vision-Language Models (LVLMs) exhibit impressive potential across various tasks but also face significant privacy risks, limiting their practical applications. Current researches on privacy assessment for LVLMs is limited in scope,…

Software systems have been evolving rapidly and inevitably introducing bugs at an increasing rate, leading to significant losses in resources consumed by software maintenance. Recently, large language models (LLMs) have demonstrated…

As on-device large language model (LLM) systems become increasingly prevalent, federated fine-tuning enables advanced language understanding and generation directly on edge devices; however, it also involves processing sensitive,…

Natural Language Processing (NLP) is an essential subset of artificial intelligence. It has become effective in several domains, such as healthcare, finance, and media, to identify perceptions, opinions, and misuse, among others. Privacy is…

Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task. However, effective strategies for fine-tuning LLMs for the QA task…

Automated Program Repair (APR) aims to fix bugs by generating patches. And existing work has demonstrated that "pre-training and fine-tuning" paradigm enables Large Language Models (LLMs) improve fixing capabilities on APR. However,…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attributes such as race, gender, age, body weight, and eye color;…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…