Related papers: Formal Verification of Local Robustness of a Class…
Results of neural network learning are always subject to some variability, due to the sensitivity to initial conditions, to convergence to local minima, and, sometimes more dramatically, to sampling variability. This paper presents a set of…
Certain forms of uncertainty that robotic systems encounter can be explicitly learned within the context of a known model, like parametric model uncertainties such as mass and moments of inertia. Quantifying such parametric uncertainty is…
In this paper, a new hierarchical software architecture is proposed to improve the safety and reliability of a safety-critical drone system from the perspective of its source code. The proposed architecture uses formal verification methods…
This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…
As hardware and software systems have grown in complexity, formal methods have been indispensable tools for rigorously specifying acceptable behaviors, synthesizing programs to meet these specifications, and validating the correctness of…
Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…
For an AI solution to evolve from a trained machine learning model into a production-ready AI system, many more things need to be considered than just the performance of the machine learning model. A production-ready AI system needs to be…
Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is…
Diagnosability is a system theoretical property characterizing whether fault occurrences in a system can always be detected within a finite time. In this paper, we investigate the verification of diagnosability for cyber-physical systems…
Availability analysis is used to assess the possible failures and their restoration process for a given system. This analysis involves the calculation of instantaneous and steady-state availabilities of the individual system components and…
Barrier certificates play an important role in verifying the safety of continuous-time systems, including autonomous driving, robotic manipulators and other critical applications. Recently, ReLU neural barrier certificates -- barrier…
Formal verification is increasingly recognized as a critical foundation for building reliable software systems. However, the need for specialized expertise to write precise specifications, navigate complex proof obligations, and learn…
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…
Deep Learning NLP domain lacks procedures for the analysis of model robustness. In this paper we propose a framework which validates robustness of any Question Answering model through model explainers. We propose that a robust model should…
Deep neural networks for medical image classification often fail to generalize consistently in clinical practice due to violations of the i.i.d. assumption and opaque decision-making. This paper examines interpretability in deep neural…
Python Testbed for Federated Learning Algorithms (PTB-FLA) is a simple FL framework targeting smart Internet of Things in edge systems that provides both generic centralized and decentralized FL algorithms, which implement the corresponding…
The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by escalating system complexity, hardware-software heterogeneity, and the integration of…
Due to the emergent adoption of distributed systems when building applications, demand for reliability and availability has increased. These properties can be achieved through replication techniques using middleware algorithms that must be…
The certification of autonomous systems is an important concern in science and industry. The KI-LOK project explores new methods for certifying and safely integrating AI components into autonomous trains. We pursued a two-layered approach:…
This article introduces a conjecture that formalises a fundamental trade-off between provable correctness and broad data-mapping capacity in Artificial Intelligence (AI) systems. When an AI system is engineered for deductively watertight…