Related papers: Securing AI Agents with Information-Flow Control
Detecting inference queries running over personal attributes and protecting such queries from leaking individual information requires tremendous effort from practitioners. To tackle this problem, we propose an end-to-end workflow for…
An information owner, possessing diverse data sources, might want to offer information services based on these sources to cooperation partners and to this end interact with these partners by receiving and sending messages, which the owner…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
This work presents insights gained by investigating the relationship between algorithmic fairness and the concept of secure information flow. The problem of enforcing secure information flow is well-studied in the context of information…
This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…
With the rise of generative AI, industry interest in software agents is growing. Given the stochastic nature of generative AI-based agents, their effective and safe deployment in organizations requires robust governance, which can be…
In an era where cyber threats are rapidly evolving, the reliability of cyber forensic analysis has become increasingly critical for effective digital investigations and cybersecurity responses. AI agents are being adopted across digital…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
Cloud computing has changed online communities in three dimensions, which are scalability, adaptability and reduced overhead. But there are serious security concerns which are brought about by its distributed and multi-tenant…
Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration,…
Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainability), security, and provenance, are also critical elements…
Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…
The integration of Generative Artificial Intelligence (AI) into autonomous machines represents a major paradigm shift in how these systems operate and unlocks new solutions to problems once deemed intractable. Although generative AI agents…
Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional AI, these systems exhibit emergent and unexpected behaviors…
We present Labeled Input Output in F* (LIO*), a verified framework that enforces information flow control (IFC) policies developed in F* and automatically extracted to C. Inspired by LIO, we encapsulated IFC policies into effects, but using…
The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better strategic planners, a…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety. As AI systems become more capable, accessible, and integrated into critical services, the dual nature of their potential is…
Artificial Intelligence (AI) agents can now orchestrate cyberattacks. This development is already increasing the speed and scale of cyber attacks, decreasing attack costs, and improving the operational autonomy of cyber capabilities. To…
As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…