Related papers: Targeted Attack on GPT-Neo for the SATML Language …

Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be extractable by simply querying the model, which poses a privacy risk. We present a novel…

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover…

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…

Model Leeching is a novel extraction attack targeting Large Language Models (LLMs), capable of distilling task-specific knowledge from a target LLM into a reduced parameter model. We demonstrate the effectiveness of our attack by extracting…

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well studied is model extraction: a phenomenon in which the…

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: *accuracy*, i.e., performing well on the…

With the advance of language models, privacy protection is receiving more attention. Training data extraction is therefore of great importance, as it can serve as a potential tool to assess privacy leakage. However, due to the difficulty of…

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by…

Machine learning models are shown to face a severe threat from Model Extraction Attacks, where a well-trained private model owned by a service provider can be stolen by an attacker pretending as a client. Unfortunately, prior works focus on…

Model extraction attacks are a kind of attacks in which an adversary obtains a new model, whose performance is equivalent to that of a target model, via query access to the target model efficiently, i.e., fewer datasets and computational…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Self-supervised learning (SSL) speech models generate meaningful representations of given clips and achieve incredible performance across various downstream tasks. Model extraction attack (MEA) often refers to an adversary stealing the…

Memorization presents a challenge for several constrained Natural Language Generation (NLG) tasks such as Neural Machine Translation (NMT), wherein the proclivity of neural models to memorize noisy and atypical samples reacts adversely with…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…