SEConvo

SEConvo consists of 1,400 chat-based social engineering conversations that mimic realistic LinkedIn reach-outs in scenarios such as Academic Collaboration, Academic Funding, Journalism, and Recruitment. All conversations are generated by GPT-4-Turbo and feature both single-LLM simulations and dual-agent interactions. 400 conversations are human-annotated.

If you find our dataset useful, please also cite our paper:

@misc{ai2024defending,      title={Defending Against Social Engineering Attacks in the Age of LLMs},       author={Lin Ai and Tharindu Kumarage and Amrita Bhattacharjee and Zizhou Liu and Zheng Hui and Michael Davinroy and James Cook and Laura Cassani and Kirill Trapeznikov and Matthias Kirchner and Arslan Basharat and Anthony Hoogs and Joshua Garland and Huan Liu and Julia Hirschberg},      year={2024},      eprint={2406.12263},      archivePrefix={arXiv},      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}

}