{"attribution":{"source":"MIT AI Risk Repository, Domain Taxonomy of AI Risks v1 (MIT AI Risk Initiative)","license":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","citation":"Slattery, P., Saeri, A. K., Grundy, E. A. C., Graham, J., Noetel, M., Uuk, R., Dao, J., Pour, S., Casper, S., & Thompson, N. (2025). The AI Risk Repository: A comprehensive meta-review, database, and taxonomy of risks from artificial intelligence. arXiv:2408.12622."},"exported_at":"2026-09-11"}
{"rows":[{"ev_id":"30.07.01","quick_ref":"Liu2024","paper_title":"Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment","level":"Risk Sub-Category","risk_category":"Robustness","risk_subcategory":"Prompt Attacks","description":"carefully controlled adversarial perturbation can flip a GPT model’s answer when used to classify text inputs. Furthermore, we find that by twisting the prompting question in a certain way, one can solicit dangerous information that the model chose to not answer","entity":"Human","intent":"Intentional","timing":"Other","domain":2,"subdomain":"2.2"},{"ev_id":"30.07.04","quick_ref":"Liu2024","paper_title":"Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment","level":"Risk Sub-Category","risk_category":"Robustness","risk_subcategory":"Poisoning Attacks","description":"fool the model by manipulating the training data, usually performed on classification models","entity":"Human","intent":"Intentional","timing":"Pre-deployment","domain":2,"subdomain":"2.2"}]}