Search

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with Long-Context Language Models (LCLMs) can automatically search massive external data and incorporate it into their contexts, enabling faithful predictions and reducing issues such as hallucinations and knowledge staleness. Existing studies targeting LCLMs mainly concentrate on addressing the so-called lost-in-the-middle problem or improving the inference effiencicy, leaving their privacy risks largely unexplored. In this paper, we aim to bridge this gap and argue that integrating all information into the long context makes it a repository of sensitive information, which often contains private data such as medical records or personal identities. We further investigate the membership privacy within LCLMs external context, with the aim of determining whether a given document or sequence is included in the LCLMs context. Our basic idea is that if a document lies in the context, it will exhibit a low generation loss or a high degree of semantic similarity to the contents generated by LCLMs. We for the first time propose six membership inference attack (MIA) strategies tailored for LCLMs and conduct extensive experiments on various popular models. Empirical results demonstrate that our attacks can accurately infer membership status in most cases, e.g., 90.66% attack F1-score on Multi-document QA datasets with LongChat-7b-v1.5-32k, highlighting significant risks of membership leakage within LCLMs input contexts. Furthermore, we examine the underlying reasons why LCLMs are susceptible to revealing such membership information.

Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist in content generation. Existing research has demonstrated potential privacy risks associated with the LLMs of RAG. However, the privacy risks posed by the integration of an external database, which often contains sensitive data such as medical records or personal identities, have remained largely unexplored. In this paper, we aim to bridge this gap by focusing on membership privacy of RAG's external database, with the aim of determining whether a given sample is part of the RAG's database. Our basic idea is that if a sample is in the external database, it will exhibit a high degree of semantic similarity to the text generated by the RAG system. We present S$^2$MIA, a \underline{M}embership \underline{I}nference \underline{A}ttack that utilizes the \underline{S}emantic \underline{S}imilarity between a given sample and the content generated by the RAG system. With our proposed S$^2$MIA, we demonstrate the potential to breach the membership privacy of the RAG database. Extensive experiment results demonstrate that S$^2$MIA can achieve a strong inference performance compared with five existing MIAs, and is able to escape from the protection of three representative defenses.

The practical needs of the ``right to be forgotten'' and poisoned data removal call for efficient \textit{machine unlearning} techniques, which enable machine learning models to unlearn, or to forget a fraction of training data and its lineage. Recent studies on machine unlearning for deep neural networks (DNNs) attempt to destroy the influence of the forgetting data by scrubbing the model parameters. However, it is prohibitively expensive due to the large dimension of the parameter space. In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model. The key idea is to shift the decision boundary of the original DNN model to imitate the decision behavior of the model retrained from scratch. We develop two novel boundary shift methods, namely Boundary Shrink and Boundary Expanding, both of which can rapidly achieve the utility and privacy guarantees. We extensively evaluate Boundary Unlearning on CIFAR-10 and Vggface2 datasets, and the results show that Boundary Unlearning can effectively forget the forgetting class on image classification and face recognition tasks, with an expected speed-up of $17\times$ and $19\times$, respectively, compared with retraining from the scratch., Comment: To be published in Proc.of 34th IEEE/CVF CVPR, 2023

Federated learning (FL) has recently emerged as a promising distributed machine learning (ML) paradigm. Practical needs of the "right to be forgotten" and countering data poisoning attacks call for efficient techniques that can remove, or unlearn, specific training data from the trained FL model. Existing unlearning techniques in the context of ML, however, are no longer in effect for FL, mainly due to the inherent distinction in the way how FL and ML learn from data. Therefore, how to enable efficient data removal from FL models remains largely under-explored. In this paper, we take the first step to fill this gap by presenting FedEraser, the first federated unlearning methodology that can eliminate the influence of a federated client's data on the global FL model while significantly reducing the time used for constructing the unlearned FL model.The basic idea of FedEraser is to trade the central server's storage for unlearned model's construction time, where FedEraser reconstructs the unlearned model by leveraging the historical parameter updates of federated clients that have been retained at the central server during the training process of FL. A novel calibration method is further developed to calibrate the retained updates, which are further used to promptly construct the unlearned model, yielding a significant speed-up to the reconstruction of the unlearned model while maintaining the model efficacy. Experiments on four realistic datasets demonstrate the effectiveness of FedEraser, with an expected speed-up of $4\times$ compared with retraining from the scratch. We envision our work as an early step in FL towards compliance with legal and ethical criteria in a fair and transparent manner., Comment: To be published in Proc.of 29th IEEE/ACM IWQoS, 2021