Related papers: Retracing the Past: LLMs Emit Training Data When T…

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have…

Scenarios in which restrictions in data transfer and storage limit the possibility to compose a single dataset -- also exploiting different data sources -- to perform a batch-based training procedure, make the development of robust models…

With the development of large language models (LLMs) like the GPT series, their widespread use across various application scenarios presents a myriad of challenges. This review initially explores the issue of domain specificity, where LLMs…

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have…

High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data used for training. This lack of transparency creates…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of…

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential…

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…

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…

Large language models (LLMs) cannot be trusted for economic forecasts during periods covered by their training data. Counterfactual forecasting ability is non-identified when the model has seen the realized values: any observed output is…

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and…

Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks (MEAs). MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and…

The drastic increase of large language models' (LLMs) parameters has led to a new research direction of fine-tuning-free downstream customization by prompts, i.e., task descriptions. While these prompt-based services (e.g. OpenAI's GPTs)…

Large language models are shown to present privacy risks through memorization of training data, and several recent works have studied such risks for the pre-training phase. Little attention, however, has been given to the fine-tuning phase…