Related papers: Are Large Pre-Trained Language Models Leaking Your…
Large language models (LLMs) require a significant redesign in solutions to preserve privacy in data-intensive applications due to their text-generation capabilities. Indeed, LLMs tend to memorize and emit private information when…
Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various…
Large language models (LLMs) are capable of producing high quality information at unprecedented rates. As these models continue to entrench themselves in society, the content they produce will become increasingly pervasive in databases that…
Language models trained via federated learning (FL) demonstrate impressive capabilities in handling complex tasks while protecting user privacy. Recent studies indicate that leveraging gradient information and prior knowledge can…
Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where humans would exercise discretion. This raises a fundamental…
Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…
Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…
Large language models (LLMs) have revolutionized how we interact with machines. However, this technological advancement has been paralleled by the emergence of "Mallas," malicious services operating underground that exploit LLMs for…
The advancements of Large Language Models (LLMs) have decentralized the responsibility for the transparency of AI usage. Specifically, LLM users are now encouraged or required to disclose the use of LLM-generated content for varied types of…
The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…
The recent surge in high-quality open-source Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, have opened the possibility of creating high-quality personalized models that generate text attuned to…
Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…
Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…
Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable…
The large language model (LLM) powered recommendation paradigm has been proposed to address the limitations of traditional recommender systems, which often struggle to handle cold start users or items with new IDs. Despite its…
Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…
Large language models (LLM) are generating information at a rapid pace, requiring users to increasingly rely and trust the data. Despite remarkable advances of LLM, Information generated by LLM is not completely trustworthy, due to…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…
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…