arXiv research

RLVR maintains safety while improving reasoning capabilities in LLMs.

Autonomous vehicles rely on machine learning to solve challenging tasks in perception and motion planning. However, automotive software safety standards have not fully evolved to address the challenges of machine learning safety such as interpretability, verification, and performance limitations. In this paper, we revi…

Fine-tuning LLMs improves capability but harms safety, study finds.

RAGuard improves safety in LLMs for offshore wind maintenance.

Survey of algorithms for testing AI-driven CPS safety.

Safe imitation learning with a safety layer for flexible training.

Deep learning methods are widely regarded as indispensable when it comes to designing perception pipelines for autonomous agents such as robots, drones or automated vehicles. The main reasons, however, for deep learning not being used for autonomous agents at large scale already are safety concerns. Deep learning appro…

This paper formalizes AI safety using hypothesis testing in GenAI.

A new algorithm for identifying the best arm in linear feedback with safety constraints.

Safety filter for unknown discrete-time systems with learned models and noise covariance.

SafeML monitors ML systems for safety and security risks.

Paper defines and quantifies safety risks in deep neural networks.

Study best arm identification with safety constraints in bandit problems.

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…

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of artificial intelligence, in particular machine learning, are statistical models. Safety …

Safe reinforcement learning tackles safety constraints with linear approximations.

Enhances safety of 3D object detection neural networks.

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…

CARL safely adapts RL agents for safety-critical tasks.

A novel approach for safe offline RL using latent safety constraints.

New method improves safety analytics by addressing imbalanced data issues.

LLM safety alignment explained as divergence estimation.

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…

Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.

Researchers introduce a method to assess the safety of interpretable machine learning models.

New method provides scalable safety guarantees for RL agents.

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…

Algorithm minimizes regret while adhering to unknown safety constraints.

The paper shows why AI safety doesn't generalize across tasks.

Study probabilistic safety of BNNs under adversarial attacks.

Safe learning of stochastic dynamics with safety constraints.

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 …

Unified control theory and machine learning for safety in uncertain systems.

Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.

A new method reduces the computational burden of safety alignment for large language models.

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…

ARTEO algorithm optimizes safety-critical systems with uncertainty.

Synthesizes machine learning applications in reliability and safety.

The paper tackles safe exploration in RL by a conservative safety critic.

High-dimensional models pose both safety benefits and risks.

CitySim dataset captures vehicle trajectories for safety research.

A new RL model ensures safe learning in uncertain environments.

This work improves safety validation of autonomous vehicles by finding interpretable failures.

AI systems that explain their decisions can be monitored for harmful intentions.

Investigates safe decision-making in interactive environments.

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…

Develops a method to simulate rare dangerous events in autonomous systems.

Every year, thousands of people receive consumer product related injuries. Research indicates that online customer reviews can be processed to autonomously identify product safety issues. Early identification of safety issues can lead to earlier recalls, and thus fewer injuries and deaths. A dataset of product reviews …