相关论文: Verifiable evaluations of machine learning models …

Recent approaches in domain-specific named entity recognition (NER), such as biomedical NER, have shown remarkable advances. However, they still lack of faithfulness, producing erroneous predictions. We assume that knowledge of entities can…

Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. Intuitively, humans…

Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a model so that its predictions satisfy explicit finite-sample…

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing…

This paper proposes a protocol for Proof of Assets of a bitcoin exchange using the Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (ZK-SNARK) without revealing either the bitcoin addresses of the exchange or balances…

Striking an optimal balance between predictive performance and fairness continues to be a fundamental challenge in machine learning. In this work, we propose a post-processing framework that facilitates fairness-aware prediction by…

Deep learning has become popular, and numerous cloud-based services are provided to help customers develop and deploy deep learning applications. Meanwhile, various attack techniques have also been discovered to stealthily compromise the…

In some situations, the interpretability of the machine learning models plays a role as important as the model accuracy. Interpretability comes from the need to trust the prediction model, verify some of its properties, or even enforce them…

Security verification of communication protocols in industrial and safety-critical systems is challenging because implementations are often proprietary, accessible only as black boxes, and too complex for manual modeling. As a result,…

Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper…

Fair predictive algorithms hinge on both equality and trust, yet inherent uncertainty in real-world data challenges our ability to make consistent, fair, and calibrated decisions. While fairly managing predictive error has been extensively…

Formal verification provides a powerful framework for proving that dynamical systems satisfy their specifications. However, these techniques face scalability challenges in high-dimensional settings, as they often rely on state-space…

Machine learning decision systems are getting omnipresent in our lives. From dating apps to rating loan seekers, algorithms affect both our well-being and future. Typically, however, these systems are not infallible. Moreover, complex…

As large language models (LLMs) are used in sensitive fields, accurately verifying their computational provenance without disclosing their training datasets poses a significant challenge, particularly in regulated sectors such as…

An interesting development in automatic visual recognition has been the emergence of tasks where it is not possible to assign objective labels to images, yet still feasible to collect annotations that reflect human judgements about them.…

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Explainability of black-box machine learning models is crucial, in particular when deployed in critical applications such as medicine or autonomous cars. Existing approaches produce explanations for the predictions of models, however, how…

Evidential deep learning, built upon belief theory and subjective logic, offers a principled and computationally efficient way to turn a deterministic neural network uncertainty-aware. The resultant evidential models can quantify…

Misinformation such as fake news is one of the big challenges of our society. Research on automated fact-checking has proposed methods based on supervised learning, but these approaches do not consider external evidence apart from labeled…

Interpretability and explainability of deep neural networks are challenging due to their scale, complexity, and the agreeable notions on which the explaining process rests. Previous work, in particular, has focused on representing internal…