Fatal accidents are a major issue hindering the wide acceptance of safety-critical systems using machine-learning and deep-learning models, such as automated-driving vehicles. Quality assurance frameworks are required for such machine learning systems, but there are no widely accepted and established quality-assurance …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Safety Assurance”
In recent years, car makers and tech companies have been racing towards self driving cars. It seems that the main parameter in this race is who will have the first car on the road. The goal of this paper is to add to the equation two additional crucial parameters. The first is standardization of safety assurance --- wh…
RAGuard improves safety in LLMs for offshore wind maintenance.
problem Conventional LLMs fail with specialised or unexpected scenarios in offshore wind maintenance.
method Integrates safety-critical documents alongside technical manuals in RAG framework.
result RAGuard increases safety recall from almost 0% to over 50% while maintaining technical recall above 60%.
Advances in the field of Machine Learning and Deep Neural Networks (DNNs) has enabled rapid development of sophisticated and autonomous systems. However, the inherent complexity to rigorously assure the safe operation of such systems hinders their real-world adoption in safety-critical domains such as aerospace and med…
New framework uses OR to ensure AI systems make safe decisions.
problem Ensuring generative AI systems make safe decisions as they gain autonomy.
method Developed a conceptual framework combining flow-based models and adversarial robustness.
result Increased autonomy requires new OR approaches for feasibility, robustness, and stress testing.
Machine learning has evolved into an enabling technology for a wide range of highly successful applications. The potential for this success to continue and accelerate has placed machine learning (ML) at the top of research, economic and political agendas. Such unprecedented interest is fuelled by a vision of ML applica…
Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.
problem Safe reinforcement learning in real environments with disturbance.
method Uses partial prior knowledge and conservative inputs to ensure state constraint satisfaction.
result Guaranteed safety with pre-specified probability in the presence of stochastic disturbance.
MC-CP combines adaptive MC dropout with conformal prediction for robust uncertainty quantification.
problem Deploying deep learning models in safety-critical applications requires reliable confidence estimates.
method MC-CP integrates adaptive Monte Carlo dropout with conformal prediction to improve model performance.
result MC-CP significantly outperforms state-of-the-art UQ methods in both classification and regression tasks.
Two-step conformal prediction method for adaptive bounding box uncertainties in multi-object detection.
problem Quantifying predictive uncertainty for multi-object detection in safety-critical applications.
method Developed a two-step conformal prediction approach to propagate uncertainty in predicted class labels into bounding box uncertainties, ensuring coverage for incorrectly classified objects.
result Desired coverage levels are satisfied with practically tight predictive uncertainty intervals on real-world datasets.
The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle). We monitor validity of mappings from sensor inputs to actuator commands, controller-focused anomaly detection (CFAM), and from actuator c…
As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assura…
Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their behavior. In this paper, we consider how formal verification techniques developed for …
People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately. Many techniques have been devised …
Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety. With the recent success of deep neural networks in various domains such as computer vision and natural language processing, researchers started …
Approach to verify neural network training integrity.
problem Poisoning attacks during neural network training.
method Use of cryptographic mechanisms to verify training integrity.
result Provable verification of neural network training integrity.
To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether inputs belonging to a bounded box can ever yield some undesirable output. Input-splitting procedures, a particular type of verification mechanism…
Proposes real-time risk monitoring for machine learning systems under unknown shifts.
problem Dynamic distribution shifts challenge real-world machine learning systems' risk assurances.
method Sequential hypothesis testing with 'testing by betting' to detect risk violations.
result Effective real-time risk monitoring under various unknown shifts.
The paper optimizes exceptions in a statistical production system using machine learning.
problem Lack of curated and labeled training data for machine learning in data quality assurance.
method Explainable supervised machine learning to identify and prioritize exceptions.
result Improvement in the quality and efficiency of exceptions generated and authenticated by users.
A new process model for machine learning applications with quality assurance.
problem Lack of standard process model for machine learning applications.
method Six-phase process model with quality assurance methodology.
result Proposes a new process model for machine learning applications.
The paper designs neural networks with assurance for controlling nonlinear systems.
problem Designing neural networks with assurance for nonlinear system control.
method Bounding the number of affine functions needed for a CPWA function, connecting it to a TLL NN architecture.
result The TLL NN architecture is parameterized by the number of affine functions in the CPWA function it realizes.
The paper uses conformal prediction to monitor CPS with machine learning components.
problem Ensuring trustworthy CPS with machine learning components.
method Conformal prediction framework for real-time assurance monitoring of CPS with machine learning.
result The method provides well-calibrated confidence and limits the number of alarms.
This paper reviews metrics to assess AI model calibration accuracy.
problem AI model probabilities do not always match their true accuracy.
method Comprehensive review of 82 probability calibration metrics.
result Identified 4 classifier families and 1 object detection family of metrics.
Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
Enhances deep learning models' robustness against adversarial attacks.
problem Lack of reliable uncertainty estimates and robust defenses for deep learning models.
method Integrates Conformal Prediction principles with adversarial training.
result Introduces OPSA-AT, a defense strategy that enhances robustness and reliability.
We tune one of the most common heating, ventilation, and air conditioning (HVAC) control loops, namely the temperature control of a room. For economical and environmental reasons, it is of prime importance to optimize the performance of this system. Buildings account from 20 to 40% of a country energy consumption, and …
We provide sufficient conditions assuring that a suitably decorated 2-polyhedron can be thickened to a compact 4-dimensional Stein domain. We also study a class of flat polyhedra in 4-manifolds and find conditions assuring that they admit Stein, compact neighborhoods. We base our calculations on Turaev's shadows suitab…
Develops ML-DQA for healthcare data quality assurance.
problem Inconsistent use of real-world data in machine learning projects.
method Develops ML-DQA framework based on RWD best practices.
result Five generalizable practices emerge from ML-DQA implementation.
PaRoT simplifies robust training for deep neural networks.
problem Training deep neural networks to be robust to small input changes.
method Developed a practical framework on TensorFlow for robust training without code modifications.
result PaRoT's performance is comparable to existing methods and is easy to use on real-world models.
A novel ML verification technique using manifold learning.
problem Ensuring trust in machine learning systems.
method Variational autoencoder for extracting a low-dimensional manifold from high-dimensional training data.
result The manifold provides diverse test data, fault-revealing test cases, and independent runtime trust assessment.
Two novel models predict bus travel times with uncertainty, improving connection assurance.
problem Improving bus connection assurance by handling travel time uncertainty.
method Two novel approaches: Deep Quantile Regression (DQR) and Bayesian Recurrent Neural Networks (BRNN).
result DQR model performs best for 80%, 90%, and 95% prediction intervals, with small underestimation.
Given a properly embedded graph Gamma in a ball B and a punctured sphere Sigma properly embedded in B - Gamma, we examine the conditions on Gamma that are necessary to assure that Sigma is boundary parallel.
RLVR maintains safety while improving reasoning capabilities in LLMs.
problem Safety-capability tradeoff in fine-tuning LLMs.
method Reinforcement Learning with Verifiable Rewards (RLVR) and theoretical analysis.
result RLVR can enhance reasoning while maintaining safety guardrails.
Deep neural networks (DNNs) are increasingly being adopted for sensing and control functions in a variety of safety and mission-critical systems such as self-driving cars, autonomous air vehicles, medical diagnostics, and industrial robotics. Failures of such systems can lead to loss of life or property, which necessit…
The paper reviews machine learning safety techniques for autonomous vehicles.
problem Challenges in machine learning safety for autonomous vehicles.
method Organizes practical safety techniques to complement engineering safety.
result Enhances dependability and safety of machine learning algorithms in autonomous vehicles.
We study the geometry of the leaf closure space of regular and singular Riemannian foliations. We give conditions which assure that this leaf space is a singular symplectic or Kähler space.
Research tackles safety of deep learning in safety-critical tasks.
problem Safety concerns of deep learning in perception tasks for autonomous agents.
method Technical enumeration and discussions on safety concerns and mitigation methods.
result Need for more mitigation methods to ensure safety of deep learning.
The paper discusses safety assessment for AI systems, focusing on machine learning models.
problem Safety assessment of AI systems, especially machine learning models, in safety-related applications.
method Analyzed AI models as statistical models and proposed a new budget allocation for AI safety.
result Safety assessment of AI systems requires a new approach focusing on the model used, not just the system.
Fine-tuning LLMs improves capability but harms safety, study finds.
problem Balancing capability and safety in LLM fine-tuning.
method Theoretical framework and numerical experiments for two safety-aware fine-tuning strategies.
result Characterization of fundamental limits of safety-capability trade-off in LLM fine-tuning.
We present a simple remark that assures that the invariant theory of certain real Lie groups coincides with that of the underlying affine, real algebraic groups. In particular, this result applies to the non-compact orthogonal or symplectic Lie groups.
Survey of algorithms for testing AI-driven CPS safety.
problem Testing AI-driven CPS for safety in complex environments.
method Survey of applied algorithms for safety validation.
result Survey of existing tools and techniques for safety validation.
Safe imitation learning with a safety layer for flexible training.
problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.
This paper formalizes AI safety using hypothesis testing in GenAI.
problem Ensuring safety of generative AI tools that create realistic content.
method Formalization of computational safety through hypothesis testing and signal processing.
result Demonstrates how AI safety can be assessed quantitatively using mathematical frameworks.
A new algorithm for identifying the best arm in linear feedback with safety constraints.
problem Identifying the best arm in linear feedback with safety constraints.
method A gap-based algorithm that ensures safety while minimizing sample complexity.
result The algorithm achieves meaningful sample complexity while ensuring safety.
Safety filter for unknown discrete-time systems with learned models and noise covariance.
problem Ensuring safety for unknown discrete-time linear systems with Gaussian noise.
method Develops a learning-based safety filter using empirical model and noise covariance, optimizing control actions to stay within safety constraints.
result Minimally modifies nominal control actions to ensure safety with high probability, tightening constraints as more data is collected.
SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measurecs.LG
SafeML monitors ML systems for safety and security risks.
problem Ensuring safety and explainability of ML systems in safety-critical domains.
method Statistical difference measures of ECDF to detect distributional shifts.
result Approach can detect invalid application contexts of ML components.
Paper defines and quantifies safety risks in deep neural networks.
problem Safety concerns in deep neural networks applied to critical sectors.
method Defines safety property, computes maximum safe radius, identifies new risk class, develops algorithm.
result Method achieves competitive performance in safety quantification.
Study best arm identification with safety constraints in bandit problems.
problem Real-world decision-making with safety constraints.
method Analyzed linear and monotonic reward and safety constraints, proposed algorithms.
result Guaranteed safe learning in both linear and general reward/safety constraint settings.
Failures are challenging for learning to control physical systems since they risk damage, time-consuming resets, and often provide little gradient information. Adding safety constraints to exploration typically requires a lot of prior knowledge and domain expertise. We present a safety measure which implicitly captures…