Rethinking Certification for Trustworthy Machine Learning-Based
Applications
- URL: http://arxiv.org/abs/2305.16822v4
- Date: Sun, 22 Oct 2023 19:31:17 GMT
- Title: Rethinking Certification for Trustworthy Machine Learning-Based
Applications
- Authors: Marco Anisetti and Claudio A. Ardagna and Nicola Bena and Ernesto
Damiani
- Abstract summary: Machine Learning (ML) is increasingly used to implement advanced applications with non-deterministic behavior.
Existing certification schemes are not immediately applicable to non-deterministic applications built on ML models.
This article analyzes the challenges and deficiencies of current certification schemes, discusses open research issues, and proposes a first certification scheme for ML-based applications.
- Score: 3.886429361348165
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Machine Learning (ML) is increasingly used to implement advanced applications
with non-deterministic behavior, which operate on the cloud-edge continuum. The
pervasive adoption of ML is urgently calling for assurance solutions assessing
applications non-functional properties (e.g., fairness, robustness, privacy)
with the aim to improve their trustworthiness. Certification has been clearly
identified by policymakers, regulators, and industrial stakeholders as the
preferred assurance technique to address this pressing need. Unfortunately,
existing certification schemes are not immediately applicable to
non-deterministic applications built on ML models. This article analyzes the
challenges and deficiencies of current certification schemes, discusses open
research issues, and proposes a first certification scheme for ML-based
applications.
Related papers
- Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [85.51252685938564]
Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML)
As with other ML models, large language models (LLMs) are prone to make incorrect predictions, hallucinate'' by fabricating claims, or simply generate low-quality output for a given input.
We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines, and provides an environment for controllable and consistent evaluation of novel techniques.
arXiv Detail & Related papers (2024-06-21T20:06:31Z) - Simulation-based Safety Assurance for an AVP System incorporating
Learning-Enabled Components [0.6526824510982802]
Testing, verification and validation AD/ADAS safety-critical applications remain as one the main challenges.
We explain the simulation-based development platform that is designed to verify and validate safety-critical learning-enabled systems.
arXiv Detail & Related papers (2023-09-28T09:00:31Z) - MLGuard: Defend Your Machine Learning Model! [3.4069804433026314]
We propose MLGuard, a new approach to specify contracts for Machine Learning applications.
Our work is intended to provide the overarching framework required for building ML applications and monitoring their safety.
arXiv Detail & Related papers (2023-09-04T06:08:11Z) - Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review [51.31851488650698]
Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid.
adversarial distortion injected into the power signal will greatly affect the system's normal control and operation.
It is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems.
arXiv Detail & Related papers (2023-08-30T03:29:26Z) - AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical
Applications with Categorical Inputs [29.907921481157974]
robustness against adversarial attacks is one of the key trust concerns for Machine Learning deployment.
We propose a provably optimal yet highly efficient adversarial robustness assessment protocol for a wide band of ML-driven cybersecurity-critical applications.
We demonstrate the use of the domain-agnostic robustness assessment method with substantial experimental study on fake news detection and intrusion detection problems.
arXiv Detail & Related papers (2022-12-13T18:12:02Z) - Toward Certification of Machine-Learning Systems for Low Criticality
Airborne Applications [0.0]
Possible airborne applications of machine learning (ML) include safety-critical functions.
Current certification standards for the aviation industry were developed prior to the ML renaissance.
There are some fundamental incompatibilities between traditional design assurance approaches and certain aspects of ML-based systems.
arXiv Detail & Related papers (2022-09-28T10:13:28Z) - Joint Differentiable Optimization and Verification for Certified
Reinforcement Learning [91.93635157885055]
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties.
We propose a framework that jointly conducts reinforcement learning and formal verification.
arXiv Detail & Related papers (2022-01-28T16:53:56Z) - Trusted Artificial Intelligence: Towards Certification of Machine
Learning Applications [5.7576910363986]
The T"UV AUSTRIA Group in cooperation with the Institute for Machine Learning at the Johannes Kepler University Linz proposes a certification process.
The holistic approach attempts to evaluate and verify the aspects of secure software development, functional requirements, data quality, data protection, and ethics.
The audit catalog can be applied to low-risk applications within the scope of supervised learning.
arXiv Detail & Related papers (2021-03-31T08:59:55Z) - White Paper Machine Learning in Certified Systems [70.24215483154184]
DEEL Project set-up the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exup'ery de Toulouse (IRT)
arXiv Detail & Related papers (2021-03-18T21:14:30Z) - Explanations of Machine Learning predictions: a mandatory step for its
application to Operational Processes [61.20223338508952]
Credit Risk Modelling plays a paramount role.
Recent machine and deep learning techniques have been applied to the task.
We suggest to use LIME technique to tackle the explainability problem in this field.
arXiv Detail & Related papers (2020-12-30T10:27:59Z) - Certified Reinforcement Learning with Logic Guidance [78.2286146954051]
We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs)
The algorithm is guaranteed to synthesise a control policy whose traces satisfy the specification with maximal probability.
arXiv Detail & Related papers (2019-02-02T20:09:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.