Related papers: When PETs misbehave: A Contextual Integrity analys…
As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…
Confidential Computing enhances privacy of data in-use through hardware-based Trusted Execution Environments (TEEs) that use attestation to verify their integrity, authenticity, and certain runtime properties, along with those of the…
This paper is concerned with the security problem for interconnected systems, where each subsystem is required to detect local attacks using locally available information and the information received from its neighboring subsystems.…
Conversational agents (CAs) (e.g., chatbots) are increasingly used in settings where users disclose sensitive information, raising significant privacy concerns. Because privacy judgments are highly contextual, supporting users to engage in…
Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context to identify and mitigate potential risks. Though researchers…
Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy,…
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…
This paper delves into the realm of ChatGPT, an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries, such as customer…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
Recent research illustrates how AI can be developed and deployed in a manner detached from the concrete social context of application. By abstracting from the contexts of AI application, practitioners also disengage from the distinct…
In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…
Personal photos of individuals when shared online, apart from exhibiting a myriad of memorable details, also reveals a wide range of private information and potentially entails privacy risks (e.g., online harassment, tracking). To mitigate…
Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using…
Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…
Real-time, online-editing web apps provide free and convenient services for collaboratively editing, sharing and storing files. The benefits of these web applications do not come for free: not only do service providers have full access to…
Privacy-enhancing technologies are technologies that implement fundamental data protection principles. With respect to biometric recognition, different types of privacy-enhancing technologies have been introduced for protecting stored…
Our online lives generate a wealth of behavioral records -'digital footprints'- which are stored and leveraged by technology platforms. This data can be used to create value for users by personalizing services. At the same time, however, it…
Privacy technologies have become extremely prevalent in recent years from secure communication channels to the Tor network. These technologies were designed to provide privacy and security for users, but these ideals have also led to…
Analyzing privacy threats in software products is an essential part of software development to ensure systems are privacy-respecting; yet it is still a far from trivial activity. While there have been many advancements in the past decade,…
Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…