Related papers: Beyond Indistinguishability: Measuring Extraction …
Indistinguishability is a fundamental principle of cryptographic security, crucial for securing data transmitted between Internet of Things (IoT) devices. This principle ensures that an attacker cannot distinguish between the encrypted…
While recent research increasingly showcases the remarkable capabilities of Large Language Models (LLMs), it is equally crucial to examine their associated risks. Among these, privacy and security vulnerabilities are particularly…
Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a…
Differential Privacy (DP) is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior…
Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision support, the model…
How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…
The energy consumption of Large Language Models (LLMs) is raising growing concerns due to their adverse effects on environmental stability and resource use. Yet, these energy costs remain largely opaque to users, especially when models are…
Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge…
Machine Learning as a Service (MLaaS) has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(\epsilon,\delta)$. Choosing…
We address the problem of defending predictive models, such as machine learning classifiers (Defender models), against membership inference attacks, in both the black-box and white-box setting, when the trainer and the trained model are…
LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications…
From buying books to finding the perfect partner, we share our most intimate wants and needs with our favourite online systems. But how far should we accept promises of privacy in the face of personal profiling? In particular we ask how can…
Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…
Privacy policies are widely used by digital services and often required for legal purposes. Many machine learning based classifiers have been developed to automate detection of different concepts in a given privacy policy, which can help…