Preventing Robotic Jailbreaking via Multimodal Domain Adaptation

Publisher ICRA

Safety Guardrails for LLM-Enabled Robots

Publisher IEEE Robotics and Automation Letters

Contextual Safety Reasoning and Grounding for Open-World Robots

Publisher ArXiv

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Publisher IJCNLP-AACL 2025

Benchmarking Misuse Mitigation Against Covert Adversaries

Publisher ArXiv

Adversarial Attacks on Robotic Vision Language Action Models

Publisher ArXiv

Jailbreaking LLM-Controlled Robots

Publisher ICRA

Jailbreaking Black Box Large Language Models in Twenty Queries

Publisher IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Publisher NeurIPS

Learning Robust Output Control Barrier Functions From Safe Expert Demonstrations

Publisher IEEE Open Journal of Control Systems

Automated black-box prompt engineering for personalized text-to-image generation

Publisher ArXiv

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks

Publisher Neural Information Processing Systems (NeurIPS)