Mitra Behzadi at SemEval-2022 Task 5 : Multimedia Automatic Misogyny Identification method based on CLIP

no code implementations • SemEval (NAACL) 2022 • Mitra Behzadi, Ali Derakhshan, Ian Harris

Everyday more users are using memes on social media platforms to convey a message with text and image combined.

Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

no code implementations • 31 Oct 2023 • JinHwa Kim, Ali Derakhshan, Ian G. Harris

Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses.