Toolkit improves neural network safety for self-driving cars.
problem Ensuring safety of neural networks in autonomous driving systems.
method Structured approach using Goal Structuring Notation and recent scientific results.
result Improves quality of a level-3 autonomous driving component.
Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and myriad other engineered sociotechnical systems, we must consider the safety of systems involving machine learning. In this paper, we first …
Safe active learning for multi-output Gaussian processes reduces data acquisition costs and ensures safety.
problem Expensive data acquisition and safety concerns in multi-output regression problems.
method Proposes a safe active learning approach considering data informativeness and safety constraints.
result Improved convergence compared to competitors on simulated and real-world datasets.
Safe Bayesian optimization tackles safety constraints in control engineering.
problem Handling safety constraints in parameter tuning of control systems.
method Lipschitz-only Safe Bayesian Optimization (LoSBO) and LoS-GP-UCB.
result SafeBO algorithms can violate safety constraints due to unreliable uncertainty bounds.
High-dimensional models pose both safety benefits and risks.
problem Emergent problems in safety alignment due to high-dimensional representations.
method Detailed visualizations and lower-dimensional subspace projections.
result Dimensional reduction preserves safety alignment while avoiding linear jailbreaking.
Synthesizes machine learning applications in reliability and safety.
problem Navigating the fragmented literature on ML for reliability and safety.
method Overview of ML categories, review of applications, discussion of Deep Learning.
result Machine learning can provide novel insights and improve accident prevention.
Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine le…
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.
Identifies open problems in quality assurance of safety-critical ML systems.
problem Quality assurance for safety-critical ML systems, especially in automated driving.
method Identified and classified open problems using automated-driving vehicles as an example.
result Open problems require interdisciplinary knowledge from various fields.
Deep learning maps road safety features from streetview imagery.
problem Accurate mapping of road safety features for safer roads.
method Proposes a deep learning approach with LSTM to capture spatial autocorrelation.
result Model outperforms baseline methods in mapping road safety features.
DriveFI uses ML to find critical faults in AVs, saving time and resources.
problem Lack of end-to-end fault assessment in AVs under realistic scenarios.
method Machine learning-based fault injection engine (DriveFI) that identifies safety-critical faults.
result Found 561 safety-critical faults in less than 4 hours, compared to weeks of random injection.
Formal constraints improve RL safety in complex environments.
problem Safety constraints in reinforcement learning for complex environments.
method Specify constraints in formal languages, instantiate as finite automata, augment MDP states, learn dense cost function.
result Improved safety in training RL algorithms over various constraints.
Holographic Invariant Storage uses vector architectures to ensure LLM safety at design time.
problem Mitigating context drift in large language models (LLMs) during deployment.
method Introduces Holographic Invariant Storage (HIS) protocol that combines known properties of bipolar Vector Symbolic Architectures into a design-time safety contract.
result Closed-form guarantees for single-signal recovery fidelity, continuous-noise robustness, and multi-signal capacity degradation are provided and validated.
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…
Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.
problem Ensuring safety in Bayesian Optimization algorithms for real-world applications.
method Investigated and improved three safety-related issues of SafeOpt-type algorithms: frequentist uncertainty bounds, RKHS norm assumptions, and discrete search spaces.
result Introduced Real-{eta}-SafeOpt, Lipschitz-only Safe Bayesian Optimization (LoSBO), and Lipschitz-only GP-UCB (LoS-GP-UCB) algorithms that retain safety guarantees and superior performance.
Study improves self-driving safety in dynamic environments.
problem Safe self-driving in non-stationary urban settings.
method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).
result Self-driving agents can adapt safely in real-time.
Unified pipeline detects multi-turn deception using geometric signals.
problem Detecting multi-turn deceptive interactions in LLMs.
method Geometric signaturization via genetic prompt optimization.
result Compact geometric model achieves high recall and F1 scores.
Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important …
Paper proposes a dataset quality process for ML systems.
problem Inadequate standards for ML datasets in safety-critical systems.
method Proposes a dataset specification and verification process.
result Demonstrates the process on a railway signal recognition system.
An innovative method optimizes engine calibration to improve efficiency and reduce emissions.
problem Complex engines with many tunable parameters require efficient calibration methods.
method Combines Principal Component Decomposition with constrained Bayesian Optimization to minimize pressure curve deviation.
result Optimal engine calibration found after 64.4s with a 0.017% efficiency gain.
Paper presents LSTMMDN for hourly bike flow estimation in Copenhagen.
problem Sparse or unavailable hourly bike flow data for safety analysis.
method Hybrid LSTM MDN model for hourly bike flow estimation.
result 66-77% more accurate bike flow estimates compared to calibration factors.
A framework integrates machine learning with robust control for safer, more reliable systems.
problem Combining machine learning with robust control for systems with stringent safety and reliability requirements.
method Integrates Gaussian Process Regression and state-of-the-art robust controller synthesis within a framework that provides rigorous guarantees.
result Demonstrated improved performance with more data while maintaining rigorous guarantees.
Efficiently identifies key input variables for expensive functions using active learning.
problem Efficiently identify key input variables for expensive, black-box functions.
method Proposes novel active learning acquisition functions targeting derivative-based global sensitivity measures (DGSMs) under Gaussian process surrogate models.
result Active learning substantially enhances sample efficiency of DGSM estimation, especially with limited evaluation budgets.
CBMs improve interpretability in RUL prediction for aircraft engines.
problem Lack of interpretability in deep learning models for asset prognostics.
method Concept Bottleneck Models (CBMs) for RUL prediction.
result CBMs achieve comparable or superior performance to black-box models while being more interpretable.
Measures policy-violating content prevalence with ML-assisted sampling and LLM labeling.
problem Accurate measurement of content violations that are often rare and costly to label.
method Design-based measurement system using ML-assisted probability sampling and LLM labeling.
result Produces unbiased prevalence estimates with confidence intervals and dashboard drilldowns.
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.
SAVED safely learns robot tasks with sparse rewards.
problem Challenges in reinforcement learning for robotics, especially sparse rewards and complex constraints.
method SAVED uses supervision to constrain exploration and learn efficiently, handling complex constraints.
result SAVED outperforms state-of-the-art methods in success rate, constraint satisfaction, and sample efficiency.
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.
Survey of technologies for trustworthy machine learning systems.
problem Building machine learning systems that are fair, explainable, auditable, and secure.
method Survey of technologies across data and model stages of machine learning.
result Four categories of system properties (fairness, explainability, auditability, safety & security) are essential for trustworthy systems.
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.
New safety measure reduces failures in learning systems.
problem Challenges in learning to control physical systems due to failures.
method Implicitly captures system dynamics to failure states using Gaussian processes for model-free active sampling.
result Significant reduction in failures during learning with estimated safety measure.
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%.
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.
aLTT selects hyperparameters efficiently with statistical guarantees.
problem Statistical validity and efficiency in hyperparameter selection.
method Sequential data-dependent multiple hypothesis testing with early termination.
result Reduces testing rounds while maintaining statistical validity.
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 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 optimizes inspection and monitoring of deteriorating structures using POMDPs.
problem Optimizing decision-making for deteriorating engineering systems with uncertain observations.
method Developed theoretical and computational foundations for Value of Information (VoI) and Value of Structural Health Monitoring (VoSHM) in POMDPs.
result POMDP policies inherently leverage VoI to guide optimal observational actions, improving long-term cost.
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.
Study evaluates machine learning methods for uncertainty quantification in complex systems.
problem Accurately quantify epistemic and aleatoric uncertainties in complex dynamical systems.
method Examined Gaussian processes, UQ-augmented neural networks (ENN, BNN, D-NN, G-NN) on two model data sets.
result Concluded on model architecture and hyperparameter tuning for improved UQ accuracy.
A scoring method for driving safety using trajectory data.
problem Managing traffic safety through driver behaviors and violations.
method Extract driving habits and violations from trajectories, train a model, score drivers.
result Proves the effectiveness of the scoring method using traffic simulation.
Safe reinforcement learning tackles safety constraints with linear approximations.
problem Ensuring safety in reinforcement learning without violating constraints.
method Modeling safety as a linear cost function, developing SLUCB-QVI and RSLUCB-QVI algorithms for MDPs with linear function approximation.
result Achieved a nearly optimal regret bound for safe reinforcement learning, matching state-of-the-art unsafe algorithms.
Enhances safety of 3D object detection neural networks.
problem Ensuring robustness and safety of 3D object detection systems.
method Symbolic error propagation, specialized loss function, safety-aware non-max-inclusion algorithm.
result Improved safety and robustness of 3D object detection neural networks.
Self-driving vehicles improve safety by predicting surrounding vehicles' trajectories.
problem Ensuring safety of self-driving vehicles through better trajectory prediction.
method Developed a Convolutional Neural Network to forecast vehicle trajectories from raw data.
result Improvement over baseline models in trajectory forecasting accuracy.