no code implementations • 9 Apr 2024 • Bibek Upadhayay, Vahid Behzadan
In this paper, we introduce a new black-box attack vector called the \emph{Sandwich attack}: a multi-language mixture attack, which manipulates state-of-the-art LLMs into generating harmful and misaligned responses.
1 code implementation • 17 Nov 2023 • Bibek Upadhayay, Vahid Behzadan
Our results indicate that the TaCo method impresses GPT-4 with an 82\% score for a low-resource language in the Vicuna Benchmark dataset, doubling the performance in contrast to instruction tuning alone.
no code implementations • 18 Nov 2022 • Bibek Upadhayay, Vahid Behzadan
Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions.
2 code implementations • 1 Sep 2020 • Bibek Upadhayay, Vahid Behzadan
The rampant integration of social media in our every day lives and culture has given rise to fast and easier access to the flow of information than ever in human history.
Cultural Vocal Bursts Intensity Prediction Emotion Recognition +3