6 papers
Differential Zonotopes for Verifying Global Robustness of DNNs
Anagha Athavale, Samuel Teuber, Matteo Maffei +3
The robustness of deep neural networks (DNNs) is critical in security-sensitive applications, where small input perturbations should not alter model predictions. This property is c…
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
S. Bensalem, Y. Dong, M. Franzle +6
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a st…
Declarative Scenario-based Testing with RoadLogic
Ezio Bartocci, Alessio Gambi, Felix Gigler +2
Scenario-based testing is a key method for cost-effective and safe validation of autonomous vehicles (AVs). Existing approaches rely on imperative scenario definitions, requiring d…
LTLGuard: Formalizing LTL Specifications with Compact Language Models and Lightweight Symbolic Reasoning
Medina Andresel, Cristinel Mateis, Dejan Nickovic +3
Translating informal requirements into formal specifications is challenging due to the ambiguity and variability of natural language (NL). This challenge is particularly pronounced…
Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving
Axel Brunnbauer, Luigi Berducci, Peter Priller +2
The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, su…
RTAMT -- Runtime Robustness Monitors with Application to CPS and Robotics
Tomoya Yamaguchi, Bardh Hoxha, Dejan Nickovic
In this paper, we present Real-Time Analog Monitoring Tool (RTAMT), a tool for quantitative monitoring of Signal Temporal Logic (STL) specifications. The library implements a flexi…