Browse AI risks

12 entries

1. 64.01.03 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   Sockpuppeting

   "Create synthetic online personas or accounts"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.1 Human Intentional Post-deployment

2. 64.02.01 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depictions of non-humans)

   Falisification

   "Fabricate or falsely represent evidence, incl. reports, IDs, documents"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.1 Human Intentional Post-deployment

3. 64.04.04 · Risk Sub-Category

   Misuse tactics to compromise GenAI systems (Model integrity)

   Model diversion

   "Model Diversion takes model manipulation one step further, by repurposing (often open-source) generative AI models in a way that diverts them from their intended functionality or from the use cases envisioned by their developers (Lin et al., 2024). An example of this is training the BERT open source model on the DarkWeb to create DarkBert.7"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.2 Human Intentional Post-deployment

4. 64.01.00 · Risk Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   -

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

5. 64.01.01 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   Impersonation

   "Assume the identity of a real person and take actions on their behalf"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

6. 64.01.02 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   Appropriated Likeness

   "Use or alter a person's likeness or other identifying features"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

7. 64.01.04 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   Non-consensual intimate imagery (NCII)

   "Create sexual explicit material using an adult person’s likeness"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

8. 64.01.05 · Risk Sub-Category

   Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

   Child sexual abuse material (CSAM)

   "Create child sexual explicit material"

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

9. 64.02.00 · Risk Category

   Misuse tactics that exploit GenAI capabilities (Realistic depictions of non-humans)

   -

   From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

   Domain 4 4.3 Human Intentional Post-deployment

10. 64.02.03 · Risk Sub-Category

    Misuse tactics that exploit GenAI capabilities (Realistic depictions of non-humans)

    Counterfeit

    "Reproduce or imitate an original work, brand or style and pass as real"

    From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

    Domain 4 4.3 Human Intentional Post-deployment

11. 64.03.00 · Risk Category

    Misuse tactics that exploit GenAI capabilities (Use of generated content)

    —

    From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

    Domain 4 4.3 Human Intentional Post-deployment

12. 64.03.02 · Risk Sub-Category

    Misuse tactics that exploit GenAI capabilities (Use of generated content)

    Targeting & Personalisation

    "Refine outputs to target individuals with tailored attacks"

    From Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024)

    Domain 4 4.3 Human Intentional Post-deployment

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.