{"url":"/dataset/harmfultasks","name":"HarmfulTasks","full_name":"Harmful and Malicious Tasks for LLMs in Jailbreaking Prompts","description_markdown":"This dataset consists of 225 malicious tasks, which were integrated into ten distinct jailbreaking prompts. The malicious tasks were divided into five categories, namely, \r\n\r\n1. Misinformation and Disinformation\r\n2. Security Threats and Cybercrimes\r\n3. Unlawful Behaviors and Activities \r\n4. Hate Speech and Discrimination \r\n5. Substance Abuse and Dangerous Practices.\r\n\r\nThe jailbreaking prompts were carefully selected to cover a diverse range of scenarios. These scenarios included role-playing, simulations, attention-shifting, and privileged execution, and the placement of the malicious task within the jailbreaking prompts was also varied.\r\n\r\nList of malicious tasks only: [https://github.com/CrystalEye42/eval-safety/blob/main/malicious_tasks_dataset.yaml](https://github.com/CrystalEye42/eval-safety/blob/main/malicious_tasks_dataset.yaml)\r\n\r\nMalicious tasks with jailbreaking prompts: [https://github.com/CrystalEye42/eval-safety/blob/main/integrated.yaml](https://github.com/CrystalEye42/eval-safety/blob/main/integrated.yaml)","description_withheld":null,"homepage":"https://github.com/CrystalEye42/eval-safety/blob/main/malicious_tasks_dataset.yaml","introduced_date":"2024-01-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/pruning-for-protection-increasing-jailbreak","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","first_author":"Adib Hasan","url":null},"license":{"name":"MIT","url":"https://github.com/CrystalEye42/eval-safety"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Adversarial Text","url":"/task/adversarial-text","datasets_with_task":"/datasets/task/adversarial-text"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HarmfulTasks"],"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."}