Yan Pang (University of Virginia), Wenlong Meng (University of Virginia), Xiaojing Liao (Indiana University Bloomington), Tianhao Wang (University of Virginia)

With the rapid development of large language models, the potential threat of their malicious use, particularly in generating phishing content, is becoming increasingly prevalent. Leveraging the capabilities of LLMs, malicious users can synthesize phishing emails that are free from spelling mistakes and other easily detectable features. Furthermore, such models can generate topic-specific phishing messages, tailoring content to the target domain and increasing the likelihood of success.

Detecting such content remains a significant challenge, as LLM-generated phishing emails often lack clear or distinguishable linguistic features. As a result, most existing semantic-level detection approaches struggle to identify them reliably. While certain LLM-based detection methods have shown promise, they suffer from high computational costs and are constrained by the performance of the underlying language model, making them impractical for large-scale deployment.

In this work, we aim to address this issue. We propose Paladin, which embeds trigger-tag associations into vanilla LLM using various insertion strategies, creating them into instrumented LLMs. When an instrumented LLM generates content related to phishing, it will automatically include detectable tags, enabling easier identification. Based on the design on implicit and explicit triggers and tags, we consider four distinct scenarios in our work. We evaluate our method from three key perspectives: stealthiness, effectiveness, and robustness, and compare it with existing baseline methods. Experimental results show that our method outperforms the baselines, achieving over 90% detection accuracy across all scenarios.

View More Papers

FidelityGPT: Correcting Decompilation Distortions with Retrieval Augmented Generation

Zhiping Zhou (Tianjin University), Xiaohong Li (Tianjin University), Ruitao Feng (Southern Cross University), Yao Zhang (Tianjin University), Yuekang Li (University of New South Wales), Wenbu Feng (Tianjin University), Yunqian Wang (Tianjin University), Yuqing Li (Tianjin University)

Read More

U.S. Election Expert Perspectives on End-to-end Verifiable Voting Systems

Julie M. Haney (National Institute of Standards and Technology, Gaithersburg, Maryland), Shanee Dawkins (National Institute of Standards and Technology, Gaithersburg, Maryland), Sandra Spickard Prettyman (Cultural Catalyst LLC, Chicago), Mary F. Theofanos (National Institute of Standards and Technology, Gaithersburg, Maryland), Kristen K. Greene (National Institute of Standards and Technology, Gaithersburg, Maryland), Kristin L. Kelly Koskey (Cultural Catalyst LLC, Chicago), Jody L. Jacobs (National Institute of Standards…

Read More

Beyond Raw Bytes: Towards Large Malware Language Models

Luke Kurlandski (Rochester Institute of Technology, Rochester New York USA), Harel Berger (Ariel University, Israel), Yin Pan (Rochester Institute of Technology, Rochester New York USA), Matthew Wright (Rochester Institute of Technology, Rochester New York USA)

Read More