Related papers: Verifiable Agentic Infrastructure: Proof-Derived A…
Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
Agentic Artificial Intelligence (AI) systems, exemplified by OpenAI's DeepResearch, autonomously pursue goals, adapting strategies through implicit learning. Unlike traditional generative AI, which is reactive to user prompts, agentic AI…
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate unbiased, privacy-preserving data while maintaining…
Every major framework for governing artificial intelligence presupposes an identifiable entity -- a developer, deployer, or operator -- who can be held responsible and compelled to comply. Decentralized AI (DeAI) dissolves this…
International agreements about AI development may be required to reduce catastrophic risks from advanced AI systems. However, agreements about such a high-stakes technology must be backed by verification mechanisms--processes or tools that…
As AI agents evolve from text generators into autonomous economic actors that accept jobs, manage budgets, and delegate to sub-agents, the absence of runtime governance becomes a critical gap. Existing frameworks orchestrate agent behavior…
The last decade has sparked several valiant efforts in deductive verification of distributed agreement protocols such as consensus and leader election. Oddly, there have been far fewer verification efforts that go beyond the core protocols…
Multi-agent systems face a fundamental architectural flaw: agent identity is bound to network location. When agents migrate between providers, scale across instances, or federate across organizations, URI-based identity schemes break…
The Update Framework or TUF was developed to address several known weaknesses that have been observed in software update distribution and validation systems. Unlike conventional secure software distribution methods where there may be a…
Large Language Models (LLMs) show promise as planners for embodied AI, but their stochastic nature lacks formal reasoning, preventing strict safety guarantees for physical deployment. Current approaches often rely on unreliable LLMs for…
Attestation is a fundamental building block to establish trust over software systems. When used in conjunction with trusted execution environments, it guarantees the genuineness of the code executed against powerful attackers and threats,…
Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a…
Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical…
Federated learning (FL) is identified as a crucial enabler for large-scale distributed machine learning (ML) without the need for local raw dataset sharing, substantially reducing privacy concerns and alleviating the isolated data problem.…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…
Cloud computing as a potential paradigm offers tremendous advantages to enterprises. With the cloud computing, the market's entrance time is reduced, computing capabilities is augmented and computing power is really limitless. Usually, to…
The growing system complexity from microservice architectures and the bilateral enhancement of artificial intelligence (AI) for both attackers and defenders presents increasing security challenges for cloud-native operations. In particular,…
Emerging deployments of Generative AI increasingly execute inference across decentralized and heterogeneous edge devices rather than on a single trusted server. In such environments, a single device failure or misbehavior can disrupt the…