相关论文: On the Foundations of Trustworthy Artificial Intel…
The problem of human trust in artificial intelligence is one of the most fundamental problems in applied machine learning. Our processes for evaluating AI trustworthiness have substantial ramifications for ML's impact on science, health,…
Deep learning (DL) algorithms are becoming ubiquitous in everyday life and in scientific research. However, the price we pay for their impressively accurate predictions is significant: their inner workings are notoriously opaque - it is…
The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…
AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases,…
Hardware-secured remote attestation is essential to establishing trust in the integrity of confidential virtual machines (cVMs), but is difficult to use in practice because verifying attestation evidence requires the use of…
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated…
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…
The rapid expansion of the Internet of Things (IoT) and Edge Computing has presented challenges for centralized Machine and Deep Learning (ML/DL) methods due to the presence of distributed data silos that hold sensitive information. To…
We describe a verification pipeline that takes production Rust cryptographic code and produces machine-checked correctness proofs in Lean 4. The pipeline combines three components: symbolic extraction tools (Charon and Aeneas, or Hax) that…
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the…
The hope of the quantum computing field is that quantum architectures are able to scale up and realize fault-tolerant quantum computing. Due to engineering challenges, such ''cheap'' error correction may be decades away. In the meantime, we…
Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their…
Attestation means providing evidence that a remote target system is worthy of trust for some sensitive interaction. Although attestation is already used in network access control, security management, and trusted execution environments, it…
How much are we to trust a decision made by an AI algorithm? Trusting an algorithm without cause may lead to abuse, and mistrusting it may similarly lead to disuse. Trust in an AI is only desirable if it is warranted; thus, calibrating…
Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal…
Powerful predictive AI systems have demonstrated great potential in augmenting human decision making. Recent empirical work has argued that the vision for optimal human-AI collaboration requires 'appropriate reliance' of humans on AI…
The appreciation and utilisation of risk and uncertainty can play a key role in helping to solve some of the many ethical issues that are posed by AI. Understanding the uncertainties can allow algorithms to make better decisions by…
This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can…
Recent legislative regulations have underlined the need for accountable and transparent artificial intelligence systems and have contributed to a growing interest in the Explainable Artificial Intelligence (XAI) field. Nonetheless, the lack…