Related papers: EigenAI: Deterministic Inference, Verifiable Resul…
Aligning AI with human values is a pressing unsolved problem. To address the lack of quantitative metrics for value alignment, we propose EigenBench: a black-box method for comparatively benchmarking language models' values. Given an…
Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…
Large-scale systems that compute analytics over a fleet of devices must achieve high privacy and security standards while also meeting data quality, usability, and resource efficiency expectations. We present a next-generation federated…
Blockchain is the underlying technology for cryptocurrencies such as Bitcoin. Blockchain is a robust distributed ledger that uses consensus algorithms to approve transactions in a decentralized manner, making malicious tampering extremely…
When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic…
Function-calling agents -- large language models that invoke tools and APIs -- require high-quality, domain-specific training data spanning executable environments, backing databases, and diverse multi-turn trajectories. We introduce…
Decentralized AI agent networks, such as Gaia, allows individuals to run customized LLMs on their own computers and then provide services to the public. However, in order to maintain service quality, the network must verify that individual…
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…
Artificial intelligence (AI) agents are increasingly capable of initiating financial transactions on behalf of users or other agents. This evolution introduces a fundamental challenge: verifying both the authenticity of an autonomous agent…
Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a permissionless…
Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation. However, EI faces…
As artificial intelligence (AI) continues to permeate various domains, concerns surrounding trust and transparency in AI-driven inference and training processes have emerged, particularly with respect to potential biases and traceability…
In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…
Generative AI (GenAI) systems promise to transform knowledge work by automating a range of tasks, yet their deployment in enterprise settings remains hindered by the lack of systematic quality assurance mechanisms. We present an Expert…
A peer-to-peer network, enabling different parties to jointly store and run computations on data while keeping the data completely private. Enigma's computational model is based on a highly optimized version of secure multi-party…
The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existing deepfake detection systems typically address a single modality and provide no mechanism…
We introduce VerifAI, an open-source expert system for biomedical question answering that integrates retrieval-augmented generation (RAG) with a novel post-hoc claim verification mechanism. Unlike standard RAG systems, VerifAI ensures…
We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that verification…
A trusted electronic election system requires that all the involved information must go public, that is, it focuses not only on transparency but also privacy issues. In other words, each ballot should be counted anonymously, correctly, and…
Edge Intelligence (EI) serves as a critical enabler for privacy-preserving systems by providing AI-empowered computation and distributed caching services at the edge, thereby minimizing latency and enhancing data privacy. The integration of…