Siheng Chen

A Backdoor Attack against 3D Point Cloud Classifiers

2021 · arXiv (Cornell University)

Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks against 3D PC classifiers are all test-time evasion (TTE) attacks …

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

2024 · arXiv (Cornell University)

Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and safety …

EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making

2025 · arXiv (Cornell University)

Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models (LLMs), with their general decision-making capabilities, offer …