Related papers: SOFT: Selective Data Obfuscation for Protecting LL…
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on…
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…
Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ…
We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…
In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…
Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provide a principled framework for auditing these risks, yet…
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…
Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model…
Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…
Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…
Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…
Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential…
Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical…
Large Language Model (LLM)-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on…
Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated…
Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform…
Fine-tuning large language models (LLMs) raises privacy concerns due to the risk of exposing sensitive training data. Federated learning (FL) mitigates this risk by keeping training samples on local devices, while facing the following…
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…
Large Language Models (LLMs) have demonstrated advanced capabilities in both text generation and comprehension, and their application to data archives might facilitate the privatization of sensitive information about the data subjects. In…