5 papers
ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
Yanjie Li, Xiangyu He, Xuelong Dai +1
Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer…
Gradient-Free Adversarial Purification with Diffusion Models
Xuelong Dai, Dong Wang, Xiuzhen Cheng +1
Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training r…
UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping
Yanjie Li, Kaisheng Liang, Bin Xiao
In recent research, adversarial attacks on person detectors using patches or static 3D model-based texture modifications have struggled with low success rates due to the flexible n…
Improving Transferable Targeted Attacks with Feature Tuning Mixup
Kaisheng Liang, Xuelong Dai, Yanjie Li +2
Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferab…
Transferable 3D Adversarial Shape Completion using Diffusion Models
Xuelong Dai, Bin Xiao
Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. How…