7 papers
SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
Zhonghao Yang, Linye Lyu, Xuanhang Chang +2
Latent Diffusion Models (LDMs) have established themselves as powerful tools in the rapidly evolving field of image generation, capable of producing highly realistic images. Howeve…
Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization
Lichen Yang, Qiang Wang, Zhonghao Yang +2
Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in handling graph-structured data; however, they exhibit failures after deployment, which can cause severe conseq…
Toward Robust and Accurate Adversarial Camouflage Generation against Vehicle Detectors
Jiawei Zhou, Linye Lyu, Daojing He +1
Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differ…
Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs
Tengyun Ma, Jiaqi Yao, Daojing He +4
Large Language Models (LLMs) have emerged as powerful tools for diverse applications. However, their uniform token processing paradigm introduces critical vulnerabilities in instru…
Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation
Zhenhua Ning, Zhuotao Tian, Shaoshuai Shi +4
Recent advances in point cloud perception have demonstrated remarkable progress in scene understanding through vision-language alignment leveraging large language models (LLMs). Ho…
One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
Linbao Li, Yannan Liu, Daojing He +1
Safety alignment in large language models (LLMs) is increasingly compromised by jailbreak attacks, which can manipulate these models to generate harmful or unintended content. Inve…