SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains von Saiem, Bijoy Ahmed, Shanto, MD Sadik Hossain, Ahsan, Rakib, Rashid, Md Rafi ur

Volltext bestellen

DFCon: Attention-Driven Supervised Contrastive Learning for Robust Deepfake Detection von Shanto, MD Sadik Hossain, Dihan, Mahir Labib, Ghosh, Souvik, Anonto, Riad Ahmed, Chowdhury, Hafijul Hoque, Muhtasim, Abir, Ahsan, Rakib, Hassan, MD Tanvir, Sojib, MD Roqunuzzaman, Hakim, Sheikh Azizul, Rahman, M. Saifur

Volltext bestellen

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains von Bijoy Ahmed Saiem, MD Sadik Hossain Shanto, Rakib Ahsan, Md Rafi ur Rashid

Volltext