Skip to content

Data poisoning attacks against local differential privacy triangle counting protocols

Data Poisoning Attacks to Locally Differentially Private Triangle Counting Protocols

arXiv: 其他 AI 安全论文· arXiv:2611.23701· Tingxuan Han, Wei Tong, Zijian Wang, Sheng Zhong·Indexed by this site · 13 hr ago· Originally publishedAttacks· Its place in the scan record →
AI summary

Local differential privacy (LDP) triangle-counting protocols are vulnerable to data poisoning attacks: small, protocol-compliant local manipulations by malicious users can be systematically amplified into large global estimation bias through reconstruction and calibration. The paper analyzes the attack surface of both non-interactive and interactive protocols, proposes a unified gain-driven framework, and instantiates it on representative protocols. Experiments on four real graph datasets show the attacks significantly distort triangle-count estimates, and existing and simple defenses are insufficient to mitigate them.

Read originalarxiv.org