7 papers
ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models
Zhuowen Yin, Chongyang Liu, Wenzhang Yang +2
Embodied Foundation Models (EFMs) integrate multimodal understanding, future-state reasoning, and executable robot actions. Yet their safety alignment for human-injury prevention r…
Modular2Simple: A Tool for Modular Scenario Creation Based on the OpenSCENARIO Format
Nikolai Khriapov, Mohamed Taha Drif, Renjue Li +1
The rapid advancement of autonomous driving systems (ADS) has introduced significant challenges, particularly in the creation of realistic and complex scenarios for testing and val…
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
Shuaitong Liu, Renjue Li, Lijia Yu +3
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computati…
Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights
Zhengyu Zhao, Hanwei Zhang, Renjue Li +6
Transferable adversarial images raise critical security concerns for computer vision systems in real-world, black-box attack scenarios. Although many transfer attacks have been pro…
Patch Synthesis for Property Repair of Deep Neural Networks
Zhiming Chi, Jianan Ma, Pengfei Yang +4
Deep neural networks (DNNs) are prone to various dependability issues, such as adversarial attacks, which hinder their adoption in safety-critical domains. Recently, NN repair tech…
Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds
Hanwei Zhang, Luo Cheng, Qisong He +6
Classification of 3D point clouds is a challenging machine learning (ML) task with important real-world applications in a spectrum from autonomous driving and robot-assisted surger…