AIBearisharXiv – CS AI · 2d ago7/10
🧠Researchers introduced NRT-Bench, a multi-turn red-teaming benchmark testing LLM agents in a simulated nuclear power plant control room. The study found that adaptive adversarial attacks succeeded in compromising critical safety functions in 8.7-12.1% of sessions across four frontier models, with vulnerabilities distributed unevenly across models rather than shared, raising concerns about LLM reliability in safety-critical deployments.
AIBullisharXiv – CS AI · Jun 107/10
🧠NOVA, a symbolic regression framework, discovers interpretable models of human driving behavior from 4.7 million real-world observations, achieving superior performance on car-following and lane-change prediction tasks. The research demonstrates that complex driving dynamics can be captured through compact algebraic structures that generalize across different freeway locations and driver populations.
$RMSE
AINeutralarXiv – CS AI · Jun 97/10
🧠Researchers propose a Human-Centered Benchmarking Framework that evaluates driver monitoring AI models across accuracy, explainability, efficiency, and robustness—rather than accuracy alone. Testing four lightweight architectures on eye-state classification reveals that while models perform similarly on clean data, each excels in different dimensions, and critically, the top-ranked model fails under sensor noise by misclassifying closed eyes as open, a safety-critical vulnerability.
AIBearisharXiv – CS AI · Jun 27/10
🧠Researchers have developed an A*-inspired framework that generates obfuscated prompts capable of triggering factual errors in large language models while preserving semantic intent. The method uses a hierarchical rewrite strategy with dynamic semantic dispersion to efficiently create adversarial prompts, demonstrating higher attack success rates than existing approaches and raising urgent concerns about LLM reliability in safety-critical applications.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers demonstrate that vision-language models (VLMs) can effectively function as zero-shot sensors for perceiving Operational Design Domains (ODDs) in autonomous systems without task-specific training. The study evaluates four VLMs on ODD classification and detection tasks, finding that chain-of-thought prompting with persona decomposition achieves optimal performance, providing a scalable approach for safety-critical autonomous driving applications.
AIBearisharXiv – CS AI · May 97/10
🧠A peer-reviewed study evaluates explainability methods in AI systems used for automatic target recognition in safety-critical applications, revealing that popular post-hoc explanation techniques have significant limitations including spurious explanations and vulnerability to manipulation. The research argues that current XAI approaches are insufficient for deployment in high-stakes environments and calls for more robust, causally-grounded methods that prioritize system assurance over visual plausibility.
AIBullisharXiv – CS AI · May 17/10
🧠OmniDrive-R1 is a new Vision-Language Model framework that addresses critical reliability failures in autonomous driving by combining perception and reasoning through an interleaved multi-modal chain-of-thought mechanism, achieving significant accuracy improvements (37.81% to 73.62%) without requiring dense localization labels.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers have developed an LLM-based framework that automatically generates safety-critical driving scenarios for autonomous vehicle testing using the CARLA simulator and realistic video synthesis. The system uses few-shot code generation to create diverse edge cases like pedestrian occlusions and vehicle cut-ins, bridging simulation and real-world realism through advanced video generation techniques.
AINeutralarXiv – CS AI · Apr 137/10
🧠Researchers introduce PilotBench, a benchmark evaluating large language models on safety-critical aviation tasks using 708 real-world flight trajectories. The study reveals a fundamental trade-off: traditional forecasters achieve superior numerical precision (7.01 MAE) while LLMs provide better instruction-following (86-89%) but with significantly degraded prediction accuracy (11-14 MAE), exposing brittleness in implicit physics reasoning for embodied AI applications.
AIBearisharXiv – CS AI · 2d ago6/10
🧠Researchers identified and corrected a critical flaw in runtime monitoring systems for autonomous agents, revealing that wall-clock-calibrated state monitors exhibit a bistable failure mode with no effective middle ground for detecting behavioral anomalies. The study demonstrates that monitoring dynamics must match the temporal characteristics of agent action streams to function properly, with implications for safety-critical AI deployment.
AIBullisharXiv – CS AI · Jun 56/10
🧠RiskFlow is a new machine learning framework that generates realistic safety-critical traffic scenarios for autonomous vehicle testing by using a single-pass velocity field model instead of iterative diffusion processes. The approach achieves faster inference times while reducing common motion artifacts and maintaining strong adversarial scenario generation capabilities.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers propose a domain-specific foundation model for safety-critical physical systems using a compact 360M-parameter language model trained on synthetic nuclear reactor simulations rather than general-purpose vision-language models. The approach demonstrates significant reliability improvements in controlled environments but is positioned as one component within a broader verification architecture, not a standalone safety solution.
AINeutralarXiv – CS AI · May 296/10
🧠Researchers present a multi-resolution deep neural network for autonomous driving that dynamically selects input resolution based on latency constraints and compute availability. The approach uses per-resolution batch normalization and resolution retargeting to optimize the tradeoff between prediction accuracy and processing speed, demonstrating improved safety metrics in CARLA simulations compared to fixed-resolution models.
AINeutralarXiv – CS AI · May 296/10
🧠Researchers introduce SCOPE, a lightweight LLM framework designed to monitor pilot readbacks of Air Traffic Control instructions, addressing a critical aviation safety gap where readback anomalies contribute to approximately 80% of aviation incidents. The system achieves 91% accuracy in detecting anomalies and 96.63% correction rates while requiring minimal computational overhead, offering a practical deployment pathway for automated safety monitoring in high-stakes operational environments.
AIBullisharXiv – CS AI · May 286/10
🧠Researchers developed SMamba-DDPG, a deep reinforcement learning framework that models how pedestrians behave differently when interacting with autonomous vehicles versus human-driven vehicles. The study found that pedestrians react faster to AVs and adopt lower crossing speeds, with AV interactions showing lower conflict rates than HDV scenarios.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers present CaTR, a reinforcement learning framework that optimizes real-time taxiway routing and conflict avoidance for multiple aircraft at airports. The system uses hierarchical traffic representation and value-decomposed learning to balance safety and efficiency, demonstrating superior performance compared to traditional planning and optimization methods while maintaining practical computational speed.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers present Hierarchical Causal Abduction (HCA), a framework that makes Model Predictive Control decisions interpretable by combining physics-informed reasoning, optimization evidence, and causal discovery. The method achieves 53% higher explanation accuracy than existing approaches across industrial control applications, addressing a critical barrier to deploying AI in safety-critical infrastructure.
AINeutralarXiv – CS AI · May 76/10
🧠Researchers present a novel Safety-by-Design method to define Operational Design Domains (ODDs) for safety-critical AI systems using data-driven approaches rather than traditional expert-led design. The approach uses kernel-based representations to retroactively characterize environmental conditions from collected data and is validated through aviation collision-avoidance system testing, potentially enabling future certification of AI systems in critical domains.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers introduce VOLTA, a simplified deep learning approach for uncertainty quantification that outperforms ten established baselines including ensemble methods and MC Dropout. The method achieves superior calibration with expected calibration error of 0.010 and competitive accuracy across multiple datasets, suggesting that complex auxiliary losses may be unnecessary for reliable uncertainty estimation in safety-critical applications.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers developed SimCert, a probabilistic certification framework that verifies behavioral similarity between compressed neural networks and their original versions. The framework addresses critical safety challenges in deploying compressed DNNs on resource-constrained systems by providing quantitative safety guarantees with adjustable confidence levels.
AINeutralarXiv – CS AI · Mar 174/10
🧠Researchers developed a symbolic machine learning approach for predicting failures in chemical processes, specifically testing on ethylene oxidation. The method outperformed traditional AI models while maintaining interpretability through rule-based systems, addressing safety concerns in chemical industries where black-box AI models are unsuitable.
