8 papers
Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy
Yu Wei, Alexander Bienstock, Antigoni Polychroniadou
The additive noise mechanism is a foundational tool for differential privacy (DP) of -dimensional real-valued vector queries. The Gaussian mechanism, utilizing Gaussian noise, i…
FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis
Shuo Liu, Xianghong Lin, Yukun Wei +1
The ubiquity of social media platforms facilitates malicious linguistic steganography, posing significant security risks. However, detection is severely hampered by two fundamental…
MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution
Yanqiu Zhao, Dongying Zheng, Kaibo Huang +3
GUI agents rely on screenshots to infer intent and operate across applications, but these screenshots often contain private messages, medical records, payment credentials, and work…
AgentMark: Utility-Preserving Behavioral Watermarking for Agents
Kaibo Huang, Jin Tan, Yukun Wei +5
LLM-based agents are increasingly deployed to autonomously solve complex tasks, raising urgent needs for IP protection and regulatory provenance. While content watermarking effecti…
ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
Wansheng Wu, Kaibo Huang, Yukun Wei +2
As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically updat…
EvoCorps: An Evolutionary Multi-Agent Framework for Depolarizing Online Discourse
Ning Lin, Haolun Li, Mingshu Liu +5
Polarization in online discourse erodes social trust and accelerates misinformation, yet technical responses remain largely diagnostic and post-hoc. Current governance approaches s…