相关论文: Contextual Integrity in LLMs via Reasoning and Rei…

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios.…

Advanced AI assistants combine frontier LLMs and tool access to autonomously perform complex tasks on behalf of users. While the helpfulness of such assistants can increase dramatically with access to user information including emails and…

Machine learning community is discovering Contextual Integrity (CI) as a useful framework to assess the privacy implications of large language models (LLMs). This is an encouraging development. The CI theory emphasizes sharing information…

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…

Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling…

Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framework, defining privacy as the appropriate flow of information…

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…

Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce…

Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding…

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where humans would exercise discretion. This raises a fundamental…

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes. Contextual Reinforcement Learning (cRL) provides a…

The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are…

Continuous Integration (CI) significantly reduces integration problems, speeds up development time, and shortens release time. However, it also introduces new challenges for quality assurance activities, including regression testing, which…

Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their…

The multicontextual nature of immersive VR makes it difficult to ensure contextual integrity of VR-generated information flows using existing privacy design and policy mechanisms. In this position paper, we call on the HCI community to do…

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…