3 papers
cs.CR2026
AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
Yuqi Jia, Ruiqi Wang, Xilong Wang +2
Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typic…
cs.LG2026
CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection
Ruiqi Wang, Ruikang Liu, Runyu Chen +4
Detecting anomalies in tabular data is critical for many real-world applications, such as credit card fraud detection. With the rapid advancements in large language models (LLMs),…
cs.CR2025
ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
Reachal Wang, Yuqi Jia, Neil Zhenqiang Gong
Prompt injection attacks aim to contaminate the input data of an LLM to mislead it into completing an attacker-chosen task instead of the intended task. In many applications and ag…