Gen-AI for User Safety: A Survey
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910818926329856 |
|---|---|
| author | Desai, Akshar Prabhu Ravi, Tejasvi Luqman, Mohammad Sharma, Mohit Kota, Nithya Yadav, Pranjul |
| author_facet | Desai, Akshar Prabhu Ravi, Tejasvi Luqman, Mohammad Sharma, Mohit Kota, Nithya Yadav, Pranjul |
| contents | Machine Learning and data mining techniques (i.e. supervised and unsupervised techniques) are used across domains to detect user safety violations. Examples include classifiers used to detect whether an email is spam or a web-page is requesting bank login information. However, existing ML/DM classifiers are limited in their ability to understand natural languages w.r.t the context and nuances. The aforementioned challenges are overcome with the arrival of Gen-AI techniques, along with their inherent ability w.r.t translation between languages, fine-tuning between various tasks and domains.
In this manuscript, we provide a comprehensive overview of the various work done while using Gen-AI techniques w.r.t user safety. In particular, we first provide the various domains (e.g. phishing, malware, content moderation, counterfeit, physical safety) across which Gen-AI techniques have been applied. Next, we provide how Gen-AI techniques can be used in conjunction with various data modalities i.e. text, images, videos, audio, executable binaries to detect violations of user-safety. Further, also provide an overview of how Gen-AI techniques can be used in an adversarial setting. We believe that this work represents the first summarization of Gen-AI techniques for user-safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06606 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Gen-AI for User Safety: A Survey Desai, Akshar Prabhu Ravi, Tejasvi Luqman, Mohammad Sharma, Mohit Kota, Nithya Yadav, Pranjul Artificial Intelligence Cryptography and Security Machine Learning and data mining techniques (i.e. supervised and unsupervised techniques) are used across domains to detect user safety violations. Examples include classifiers used to detect whether an email is spam or a web-page is requesting bank login information. However, existing ML/DM classifiers are limited in their ability to understand natural languages w.r.t the context and nuances. The aforementioned challenges are overcome with the arrival of Gen-AI techniques, along with their inherent ability w.r.t translation between languages, fine-tuning between various tasks and domains. In this manuscript, we provide a comprehensive overview of the various work done while using Gen-AI techniques w.r.t user safety. In particular, we first provide the various domains (e.g. phishing, malware, content moderation, counterfeit, physical safety) across which Gen-AI techniques have been applied. Next, we provide how Gen-AI techniques can be used in conjunction with various data modalities i.e. text, images, videos, audio, executable binaries to detect violations of user-safety. Further, also provide an overview of how Gen-AI techniques can be used in an adversarial setting. We believe that this work represents the first summarization of Gen-AI techniques for user-safety. |
| title | Gen-AI for User Safety: A Survey |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2411.06606 |