{"url":"/dataset/mhj","name":"MHJ","full_name":"Multi-Turn Human Jailbreaks","description_markdown":"We compile successful jailbreaks into the Multi-Turn Human Jailbreaks (MHJ) dataset, consisting of 2,912 prompts across 537 multi-turn conversations. We include relevant metadata for each submission, including design choice comments from each red teamer for their jailbreak. The resulting attack success rate (ASR) of our human red teaming is shown as follows.","description_withheld":null,"homepage":"https://huggingface.co/datasets/ScaleAI/mhj","introduced_date":"2024-08-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/llm-defenses-are-not-robust-to-multi-turn","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","first_author":"Nathaniel Li","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["MHJ"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}