期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
Evaluating Privacy Leakage and Memorization Attacks on Large Language Models (LLMs) in Generative AI Applications 被引量:1
1
作者 Harshvardhan Aditya Siddansh Chawla +6 位作者 Gunika Dhingra Parijat Rai Saumil Sood Tanmay Singh zeba mohsin wase Arshdeep Bahga Vijay K. Madisetti 《Journal of Software Engineering and Applications》 2024年第5期421-447,共27页
The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Infor... The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. We describe different black-box attacks from potential adversaries and study their impact on the amount and type of information that may be recovered from commonly used and deployed LLMs. Our research investigates the relationship between PII leakage, memorization, and factors such as model size, architecture, and the nature of attacks employed. The study utilizes two broad categories of attacks: PII leakage-focused attacks (auto-completion and extraction attacks) and memorization-focused attacks (various membership inference attacks). The findings from these investigations are quantified using an array of evaluative metrics, providing a detailed understanding of LLM vulnerabilities and the effectiveness of different attacks. 展开更多
关键词 Large Language Models PII Leakage Privacy Memorization OVERFITTING Membership Inference Attack (MIA)
下载PDF
Protecting LLMs against Privacy Attacks While Preserving Utility
2
作者 Gunika Dhingra Saumil Sood +2 位作者 zeba mohsin wase Arshdeep Bahga Vijay K. Madisetti 《Journal of Information Security》 2024年第4期448-473,共26页
The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Infor... The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. This inadvertent leakage of sensitive information typically occurs when the models are subjected to black-box attacks. To address the growing concerns of safeguarding private and sensitive information while simultaneously preserving its utility, we analyze the performance of Targeted Catastrophic Forgetting (TCF). TCF involves preserving targeted pieces of sensitive information within datasets through an iterative pipeline which significantly reduces the likelihood of such information being leaked or reproduced by the model during black-box attacks, such as the autocompletion attack in our case. The experiments conducted using TCF evidently demonstrate its capability to reduce the extraction of PII while still preserving the context and utility of the target application. 展开更多
关键词 Large Language Models PII Leakage PRIVACY Memorization Membership Inference Attack (MIA) DEFENSES Generative Adversarial Networks (GANs) Synthetic Data
下载PDF
Object Detection Meets LLMs: Model Fusion for Safety and Security
3
作者 zeba mohsin wase Vijay K. Madisetti Arshdeep Bahga 《Journal of Software Engineering and Applications》 2023年第12期672-684,共13页
This paper proposes a novel model fusion approach to enhance predictive capabilities of vision and language models by strategically integrating object detection and large language models. We have named this multimodal... This paper proposes a novel model fusion approach to enhance predictive capabilities of vision and language models by strategically integrating object detection and large language models. We have named this multimodal integration approach as VOLTRON (Vision Object Linguistic Translation for Responsive Observation and Narration). VOLTRON is aimed at improving responses for self-driving vehicles in detecting small objects crossing roads and identifying merged or narrower lanes. The models are fused using a single layer to provide LLaMA2 (Large Language Model Meta AI) with object detection probabilities from YoloV8-n (You Only Look Once) translated into sentences. Experiments using specialized datasets showed accuracy improvements up to 88.16%. We provide a comprehensive exploration of the theoretical aspects that inform our model fusion approach, detailing the fundamental principles upon which it is built. Moreover, we elucidate the intricacies of the methodologies employed for merging these two disparate models, shedding light on the techniques and strategies used. 展开更多
关键词 Computer Vision Large Language Models Self Driving Vehicles
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部