3 papers
cs.AI2026
Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification
Qian Ma, Anna Squicciarini, Sarah Rajtmajer
Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existing authorship obfuscation met…
cs.CR2024
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
Feiran Jia, Tong Wu, Xin Qin +1
Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhance…
cs.HC2023
Losing One's Story: How Vulnerable Users Experience Harm in Online Support Seeking
Yingfan Zhou, Priya Kumar, Anna Squicciarini +1
Online support communities are a critical resource for individuals facing distress, stigma, and limited offline support. However, these spaces are not uniformly supportive, particu…