Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916296258486272 |
|---|---|
| author | Marchal, Nahema Xu, Rachel Elasmar, Rasmi Gabriel, Iason Goldberg, Beth Isaac, William |
| author_facet | Marchal, Nahema Xu, Rachel Elasmar, Rasmi Gabriel, Iason Goldberg, Beth Isaac, William |
| contents | Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for malicious purposes. However, we still lack a concrete understanding of how GenAI models are specifically exploited or abused in practice, including the tactics employed to inflict harm. In this paper, we present a taxonomy of GenAI misuse tactics, informed by existing academic literature and a qualitative analysis of approximately 200 observed incidents of misuse reported between January 2023 and March 2024. Through this analysis, we illuminate key and novel patterns in misuse during this time period, including potential motivations, strategies, and how attackers leverage and abuse system capabilities across modalities (e.g. image, text, audio, video) in the wild. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13843 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data Marchal, Nahema Xu, Rachel Elasmar, Rasmi Gabriel, Iason Goldberg, Beth Isaac, William Artificial Intelligence Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for malicious purposes. However, we still lack a concrete understanding of how GenAI models are specifically exploited or abused in practice, including the tactics employed to inflict harm. In this paper, we present a taxonomy of GenAI misuse tactics, informed by existing academic literature and a qualitative analysis of approximately 200 observed incidents of misuse reported between January 2023 and March 2024. Through this analysis, we illuminate key and novel patterns in misuse during this time period, including potential motivations, strategies, and how attackers leverage and abuse system capabilities across modalities (e.g. image, text, audio, video) in the wild. |
| title | Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.13843 |