8 papers
OBJVanish: Physically Realizable Text-to-3D Adv. Generation of LiDAR-Invisible Objects
Bing Li, Wuqi Wang, Yanan Zhang +6
LiDAR-based 3D object detectors are fundamental to autonomous driving, where failing to detect objects poses severe safety risks. Developing effective 3D adversarial attacks is ess…
FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
Gabriel Tjio, Jie Zhang, Xulei Yang +6
Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for…
DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
Yun Xing, Yue Cao, Nhat Chung +6
Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situation…
Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
Ying Yang, Jie Zhang, Xiao Lv +3
While adversarial attacks on vision-and-language pretraining (VLP) models have been explored, generating natural adversarial samples crafted through realistic and semantically mean…
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Qi Zhou, Jie Zhang, Dongxia Wang +5
Human preference plays a crucial role in the refinement of large language models (LLMs). However, collecting human preference feedback is costly and most existing datasets neglect…
CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
Zhenhong Zhou, Zherui Li, Jie Zhang +4
Large Language Model-based Multi-Agent Systems (LLM-MASs) have demonstrated remarkable real-world capabilities, effectively collaborating to complete complex tasks. While these sys…