# Multi-Adversarial Safety Analysis for Autonomous Vehicles

arXiv: https://arxiv.org/abs/2112.14344 · HTML: https://mlsanity.com/paper/2112.14344/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2021.

## Built on by (most cited first, 2 of 2)

- [Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security](https://mlsanity.com/paper/2401.10313/) (2024)
- [ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning](https://mlsanity.com/paper/2610.07323/) (2026)

## Abstract (arXiv)

This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different modelling strategies yield very different behaviors regardless of the validity of the strategies in other scenarios. Given the nature of real-life driving scenarios, we propose a modeling strategy in our formulation that accounts for subtle interactions between agents, and compare its Hamiltonian results to other baselines. Our formulation encourages reduction of conservativeness in Hamilton-Jacobi safety analysis to provide better safety guarantees during navigation.