Dataset Groups Activity Stream AdvBench The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models. BibTex: @dataset{Xiaomeng_Hu_and_Pin-Yu_Chen_and_Tsung-Yi_Ho_2024, abstract = {The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.}, author = {Xiaomeng Hu and Pin-Yu Chen and Tsung-Yi Ho}, doi = {10.57702/iqh9imd4}, institution = {No Organization}, keyword = {'AdvBench', 'Adversarial Examples', 'adversarial attacks', 'dataset', 'jailbreak attack', 'large language model', 'natural language processing'}, month = {dec}, publisher = {TIB}, title = {AdvBench}, url = {https://service.tib.eu/ldmservice/dataset/advbench}, year = {2024} }
