Contextual integrity
PulseAugur coverage of Contextual integrity — every cluster mentioning Contextual integrity across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New generative model studies contextual integrity in LLM information sharing
Researchers have developed a generative model to study contextual integrity in information sharing, particularly concerning large language models. This model simulates conversations between two actors, one with private …
-
New framework TG-CI enhances privacy in multi-agent LLM systems
Researchers have introduced Task-Graph Contextual Integrity (TG-CI), a novel framework designed to enhance privacy in multi-agent Large Language Model (LLM) systems. Unlike existing methods that assess disclosures in is…
-
New benchmark reveals agentic AI models leak more sensitive data with increased capability
A new benchmark, CIMEMORIES DIALOGUE, has been developed to assess privacy leakage in agentic dialogue systems. This benchmark, comprising 4,410 dialogue instances, evaluates how well models handle sensitive information…
-
Mastodon launches research initiative for context-aware AI
Mastodon is initiating a research project focused on developing context-aware AI systems designed to better comprehend the subtleties of human-AI communication. The initiative aims to advance the understanding and appli…
-
AI agents' security and privacy risks detailed in new research and workshop
Multiple research papers and a Google workshop report highlight the critical need for enhanced security and privacy measures in autonomous AI agents. These works address challenges such as unstructured input ambiguity, …
-
LLMs struggle with contextual integrity, leaking sensitive data up to 69% of the time
New research highlights significant challenges in maintaining contextual integrity within large language models (LLMs). A benchmark called CIMemories revealed that even advanced models like GPT-5 can exhibit up to 69% a…
-
Bruce Schneier explores contextual integrity in LLMs
Bruce Schneier's blog discusses the concept of contextual integrity in relation to Large Language Models (LLMs). He highlights two academic papers that explore this topic, emphasizing its importance for AI and integrity…
-
New AI Research Focuses on Privacy in Agent Collaboration
Two new research papers propose methods for enhancing privacy in AI agent collaborations. The first, DiSan, uses a two-stream encoder to disentangle task semantics from source-identifying style in text, enabling joint t…
-
New LLM benchmark tests privacy; Ollama enables local AI
Researchers have developed IDP-Bench, a new benchmark designed to evaluate how well large language models (LLMs) can protect personal information in interdependent privacy scenarios. The benchmark, which uses the Contex…