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.
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.
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.
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.
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.
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%.
Researchers introduce a method to assess the safety of interpretable machine learning models.
problem Ensuring safety in machine learning models that are easy to understand.
method Introduce maximum deviation as an optimization problem to find the largest deviation from a safe reference model.
result Interpretability helps in assessing the safety of machine learning models.
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.
CARL safely adapts RL agents for safety-critical tasks.
problem Safety hazards in RL for safety-critical tasks.
method CARL combines model-based RL and cautious adaptation.
result CARL achieves higher rewards with fewer failures in safety-critical tasks.
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.
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…
LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
Unified control theory and machine learning for safety in uncertain systems.
problem Safety guarantees for systems with measurement model uncertainty.
method Measurement-Robust Control Barrier Functions (MR-CBFs) for control synthesis.
result MR-CBFs ensure safety in perception systems with measurement model uncertainty.
A new method reduces the computational burden of safety alignment for large language models.
problem Safety concerns in large language models and the need to align them with human preferences.
method Optimal dualization approach to reduce constrained alignment to an unconstrained problem.
result Our algorithms MoCAN and PeCAN significantly reduce computational burden and improve training stability.
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.
By building on a recently introduced genetic-inspired attribute-based conceptual framework for safety risk analysis, we propose a novel methodology to compute construction univariate and bivariate construction safety risk at a situational level. Our fully data-driven approach provides construction practitioners and aca…
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.
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.
Each year, around 6 million car accidents occur in the U.S. on average. Road safety features (e.g., concrete barriers, metal crash barriers, rumble strips) play an important role in preventing or mitigating vehicle crashes. Accurate maps of road safety features is an important component of safety management systems for…
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.
A new RL model ensures safe learning in uncertain environments.
problem Safe reinforcement learning in uncertain, partially observable environments.
method Lyapunov-based uncertainty quantification and Transformers for memory.
result Significant improvement in safety and optimality in grid-world tasks.
Study evaluates conformal prediction methods for safety in vision models under shifts and long-tailed data.
problem Safety guarantees of conformal prediction methods under distribution shifts and long-tailed data.
method Empirical evaluation of post-hoc and training-based conformal prediction methods on large-scale datasets and models.
result Performance of conformal prediction methods degrades significantly under distribution shifts and long-tailed data.
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
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…
Neural network predicts nonlinear safety behavior based on personality traits.
problem Predicting construction workers' unsafe behaviors based on personality traits.
method Developed a forecasting model using neural network algorithms.
result Nonlinear relationship exists between personality traits and safety behavior.
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks. A key problem is how to ensure safety of the learned policy---e.g., that a walking robot does not fall over or that an autonomous car does not run into an obstacle. We focus on the setting where the dynamics are know…
System predicts ice formation to improve road safety.
problem Improving road safety through accurate ice formation prediction.
method Combining physical models and machine learning for data correction.
result Machine learning effectively corrects incorrect data in forecasts.
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.
Algorithm minimizes regret while adhering to unknown safety constraints.
problem Online learning with unknown safety constraints.
method General meta-algorithm leveraging online regression and learning oracles.
result Concrete algorithm with T \sqrt{T} T regret for linear constraints. A new framework ensures model safety by retaining old model capabilities while improving new tasks.
problem Catastrophic forgetting in continual learning systems.
method Retention-centric framework with data-dependent constraints and an efficient constrained optimization algorithm.
result The method ensures that new models retain important capabilities of old models while improving new tasks.
Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers' behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety…
Safe learning of stochastic dynamics with safety constraints.
problem Learning controlled stochastic dynamics with safety constraints.
method Iterative expansion of a safe control set using kernel-based confidence bounds.
result The method ensures safe exploration and efficient estimation of system dynamics.
Model forecasts motor vehicle collision rates with high accuracy.
problem Forecasting motor vehicle collision rates with high accuracy.
method Adopted Heston Stochastic Volatility model and extended it to account for seasonality and accelerated safety periods.
result Short-term forecasts show high accuracy (over 95%) and outperform existing models.
ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…
Although aviation accidents are rare, safety incidents occur more frequently and require a careful analysis to detect and mitigate risks in a timely manner. Analyzing safety incidents using operational data and producing event-based explanations is invaluable to airline companies as well as to governing organizations s…
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.
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 …
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.
Meta-learning priors improves safe Bayesian optimization.
problem Optimizing robot controllers under safety constraints.
method Meta-learning priors from offline data using F-PACOH.
result Meta-learned priors accelerate safe BO convergence.
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.
A new error bound improves safety in Bayesian optimization.
problem Ensuring safety in Bayesian optimization with probabilistic models.
method Introducing a novel error bound using Wiener kernel regression for Gaussian processes and noise.
result The new error bound provides larger safety regions than previous methods.
AI systems that explain their decisions can be monitored for harmful intentions.
problem Monitoring AI systems' decision-making processes for harmful intentions is imperfect and can miss some misbehavior.
method Monitoring the chain of thought (CoT) of AI systems that communicate in human language.
result CoT monitoring is a promising but fragile approach to AI safety.
We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form of first-order logic constraints into a TNN model, where rules that encode safet…
Study examines sample complexity for RL with safety constraints.
problem Ensuring safety in RL for systems with constraints.
method Analyzes two RL approaches: generative and online.
result Sample complexity increased by a logarithmic factor in constraints.
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.
Develops a method to simulate rare dangerous events in autonomous systems.
problem Rare dangerous events in safety-critical systems are hard to test in real-world settings.
method Combines exploration, exploitation, and optimization techniques for rare-event simulation.
result Provides rigorous guarantees for the performance of the method.
SafeQ-Learning uses Wasserstein DRO to ensure safety in online learning.
problem Ensuring safety in online Q-Learning algorithms.
method DrQ algorithm that uses Wasserstein ambiguity sets and offset variables.
result SafeQ-Learning provides idealistic probabilistic safety guarantees.