2 papers
cs.CR2025
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
Zonghao Ying, Siyang Wu, Run Hao +44
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks…
cs.RO2025
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios
Jingzheng Li, Xianglong Liu, Shikui Wei +6
Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception task and the development of end-to-end autonomous d…