Anna Squicciarini — accepted AI-conference papers

2025

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Feiran Jia, Tong Wu, Xin Qin, Anna Squicciarini

ACL 2025long

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process various data sources, while powerful, introduces significant sec…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Content Sharing Design for Social Welfare in Networked Disclosure Game

Feiran Jia, Chenxi Qiu, Sarah Rajtmajer, Anna Squicciarini

UAI 2023poster

This work models the costs and benefits of personal information sharing, or self-disclosure, in online social networks as a networked disclosure game. In a networked population where edges represent visibility amongst users, we assume a leader can influence network structure through content promotio…

Cited by 2 Source ↗PDF ↗Scholar ↗