相关论文: Towards Verifiable AI with Lightweight Cryptograph…

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…

We propose a security verification framework for cryptographic protocols using machine learning. In recent years, as cryptographic protocols have become more complex, research on automatic verification techniques has been focused on. The…

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM…

Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…

In an emerging computing paradigm, computational capabilities, from processing power to storage capacities, are offered to users over communication networks as a cloud-based service. There, demanding computations are outsourced in order to…

As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the…

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…

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…

Regulated AI workflows (such as clinical trials, medical decision support, and financial compliance) must satisfy strict auditability and integrity requirements. Existing audit-trail mechanisms rely on variable-length records, bulky…

When computation is outsourced, the data owner would like to be assured that the desired computation has been performed correctly by the service provider. In theory, proof systems can give the necessary assurance, but prior work is not…

The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…

When delegating computation to a service provider, as in cloud computing, we seek some reassurance that the output is correct and complete. Yet recomputing the output as a check is inefficient and expensive, and it may not even be feasible…

Informal arguments that cryptographic protocols are secure can be made rigorous using inductive definitions. The approach is based on ordinary predicate calculus and copes with infinite-state systems. Proofs are generated using…

Transparency protocols are protocols whose actions can be publicly monitored by observers (such observers may include regulators, rights advocacy groups, or the general public). The observed actions are typically usages of private keys such…

In this paper, we present VerifyML, the first secure inference framework to check the fairness degree of a given Machine learning (ML) model. VerifyML is generic and is immune to any obstruction by the malicious model holder during the…

As the cloud computing paradigm has gained prominence, the need for verifiable computation has grown increasingly urgent. The concept of verifiable computation enables a weak client to outsource difficult computations to a powerful, but…

Generative AI models, such as GPT-4 and Stable Diffusion, have demonstrated powerful and disruptive capabilities in natural language and image tasks. However, deploying these models in decentralized environments remains challenging. Unlike…

High availability of data is responsible for the current trends in Artificial Intelligence (AI) and Machine Learning (ML). However, high-grade datasets are reluctantly shared between actors because of lacking trust and fear of losing…

Private Transformer inference using cryptographic protocols offers promising solutions for privacy-preserving machine learning; however, it still faces significant runtime overhead (efficiency issues) and challenges in handling long-token…

Cryptographic protocols play a fundamental role in securing modern digital infrastructure, but they are often deployed without prior formal verification. This could lead to the adoption of distributed systems vulnerable to attack vectors.…