MIT AI Risk Repository · domain 1: Discrimination & Toxicity
1.1 Unfair discrimination and misrepresentation
Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and representation of those groups.
- 83
- 12
- 118
- 58
| Label | Value |
|---|---|
| AI | 58 |
| Other | 13 |
| Human | 11 |
| Not coded | 1 |
| Label | Value |
|---|---|
| Unintentional | 64 |
| Other | 16 |
| Intentional | 2 |
| Not coded | 1 |
| Label | Value |
|---|---|
| Post-deployment | 50 |
| Other | 19 |
| Pre-deployment | 13 |
| Not coded | 1 |
| Label | Value |
|---|---|
| 2012 | 5 |
| 2013 | 2 |
| 2014 | 2 |
| 2015 | 6 |
| 2016 | 13 |
| 2017 | 9 |
| 2018 | 9 |
| 2019 | 8 |
| 2020 | 19 |
| 2021 | 8 |
| 2022 | 10 |
| 2023 | 11 |
| 2024 | 7 |
| 2025 | 3 |
| Label | Value |
|---|---|
| Risk Category | 22 |
| Risk Sub-Category | 61 |
Risk entries
Browse and export all- AI discrimination
"AI discrimination is a challenge raised by many researchers and governments and refers to the prevention of bias and injustice caused by the actions of AI systems (Bostrom & Yudkowsky, 2014; Weyerer...
- Lack of data, poor data quality, and biases in training data
- Unfair statistical AI decisions and discrimination of minorities
- Operational misuses (Automated decision-making)
- Hate/Toxicity (Perpetuating Harmful Beliefs)
- Discrimination/Bias (Protected Characteristics)
- Data bias
"Specifically, data bias refers to certain groups or certain types of elements that are over-weighted or over-represented than others in AI/ ML models, or variables that are crucial to characterize a...
- Model bias
"While data bias is a major contributor of model bias, model bias actually manifests itself in different forms and shapes, such as presentation bias, model evaluation bias, and popularity bias. In add...