CORTEXA
← Browse
arxivcs.AI2026-06-30

Revealing Safety-Critical Scenarios for UTM via Transformer

Huaze Tang, Bill Zeng, Chao Wang, Zhenpeng Shi, Qian Zhang, Wenbo Ding

Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the ``long-tail effect'' of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8$\times$ improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.

View free PDFSource page

Related papers

arxivcs.ROcs.AI2026-07-07

OmniSCS: Omni Safety-Critical Scenario Synthesis for Autonomous Driving via a Fully Editable Driving World

Xiaoyun Dong, Qian Xu, Yang Lu, Yang Lou, Yung-Hui Li, Jianping Wang

The synthesis of safety-critical scenarios (SCS) and their evaluation through closed-loop simulations are crucial for developing robust autonomous driving systems. A key aspect of this process involves editing agent states in both appearance and trajectory levels within existing…

View free PDFSource page
arxivcs.SEcs.AI2026-07-03

Detecting Architectural Drift in Safety-Critical Firmware through Runtime Trace Analysis

Domenico Francesco De Angelis, Marco De Luca, Domenico Amalfitano, Pasquale Cimmino, Anna Rita Fasolino

Maintaining consistency between architectural design and runtime-observed behavior is challenging in long-lived safety-critical firmware. This paper presents a runtime-informed methodology for detecting architectural drift in ISO 26262-compliant firmware. The approach collects ha…

View free PDFSource page
arxivcs.CYcs.AIcs.HC2026-07-21

The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

Gjergji Kasneci, Enkelejda Kasneci

Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios. That focus is incomplete. In deployed systems, many of the most consequential failures are quieter: plausible rathe…

View free PDFSource page
arxivcs.AIcs.MA2026-07-02

Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems

Uwe M. Borghoff, Paolo Bottoni, Remo Pareschi

Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large language models, world models, optimization engines, specialized neural architectures, autonomous platforms, and human operators. While much current research focuses on improv…

View free PDFSource page
arxivcs.LGcs.AI2026-06-29

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, Wieland Brendel, Martin Jaggi

Looped Transformers, which repeatedly apply a shared transformer block, are an architecturally natural fit for variable-length algorithmic tasks. Although they can exhibit strong length generalization beyond the length of training sequences, this behavior is brittle, yielding hig…

View free PDFSource page
arxivcs.AIcs.CCcs.CRcs.LG2026-07-03

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

Liyan Chen, Yael Tauman Kalai, Zoe Xi

As AI models continue to develop powerful capabilities, it becomes critical that we are able to verify that their output is aligned with our intentions. A recent line of work focuses on verification via debate, a model of interactive proofs where two competing powerful provers, o…

View free PDFSource page