arXiv research

Extends neural net safety guarantees by proving structural properties.

Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these networks have been shown to often mispredict on inputs with minor adversarial or even accidental perturbations. Consequences of such errors can …

RLVR maintains safety while improving reasoning capabilities in LLMs.

ART trains neural nets to be both accurate and safe.

Holographic Invariant Storage uses vector architectures to ensure LLM safety at design time.

Paper defines and quantifies safety risks in deep neural networks.

Deriving the optimal safety stock quantity with which to meet customer satisfaction is one of the most important topics in stock management. However, it is difficult to control the stock management of correlated marketable merchandise when using an inventory control method that was developed under the assumption that t…

New method provides scalable safety guarantees for RL agents.

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

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

Safe RL in linear systems achieves $\sqrt{T}$-regret.

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at least as well as a baseline. In this paper, we study the issue of safety in cont…

Paper proposes Vertex Networks for reinforcement learning of control systems with safety guarantees.

This work provides safety guarantees for iterative GP predictions.

The paper reviews machine learning safety techniques for autonomous vehicles.

Research tackles safety of deep learning in safety-critical tasks.

The paper discusses safety assessment for AI systems, focusing on machine learning models.

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

New safety measure reduces failures in learning systems.

Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.

RAGuard improves safety in LLMs for offshore wind maintenance.

Survey of algorithms for testing AI-driven CPS safety.

The paper evaluates Bayesian neural networks for safety in autonomous driving.

PEREGRiNN verifies safety of ReLU NNs by penalizing relaxation in a greedy manner.

Safe imitation learning with a safety layer for flexible training.

This paper formalizes AI safety using hypothesis testing in GenAI.

Deep learning maps road safety features from streetview imagery.

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.

Study best arm identification with safety constraints in bandit problems.

Safe reinforcement learning tackles safety constraints with linear approximations.

Enhances safety of 3D object detection neural networks.

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.

Survey of technologies for trustworthy machine learning systems.

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…

MARLeME extracts MARL models into symbolic models for better interpretability.

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.

Recent advances in machine learning and artificial intelligence are now being considered in safety-critical autonomous systems where software defects may cause severe harm to humans and the environment. Design organizations in these domains are currently unable to provide convincing arguments that their systems are saf…

Study uses deep learning to quickly estimate tissue properties for personalized radio-frequency dosimetry.

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.

Study probabilistic safety of BNNs under adversarial attacks.

Formal constraints improve RL safety in complex environments.