AAAI 2025technical0 citations
All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract)
Arka Dutta, Aman Priyanshu, Ashiqur R. KhudaBukhsh
Abstract
This paper makes a novel combination of a recently proposed bias audit framework and a recently proposed jailbreaking technique for Llama3. On an audit comprising several disadvantaged groups, our experiments reveal that a jailbroken Llama3 exhibits worrisome antisemitism, racism, misogyny, and homophobia (to list a few) much akin to a broad suite of LLMs that were susceptible to similar biases.
BibTeX
@article{Dutta_Priyanshu_KhudaBukhsh_2025, title={All You Need Is S P A C E: When Jailbreaking Meets Bias Audit and Reveals What Lies Beneath the Guardrails (Student Abstract)}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35249}, DOI={10.1609/aaai.v39i28.35249}, abstractNote={This paper makes a novel combination of a recently proposed bias audit framework and a recently proposed jailbreaking technique for Llama3. On an audit comprising several disadvantaged groups, our experiments reveal that a jailbroken Llama3 exhibits worrisome antisemitism, racism, misogyny, and homophobia (to list a few) much akin to a broad suite of LLMs that were susceptible to similar biases.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Dutta, Arka and Priyanshu, Aman and KhudaBukhsh, Ashiqur R.}, year={2025}, month={Apr.}, pages={29353-29355} }