Trustworthy AI: Safety, Bias, and Privacy -- A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916789554774016 |
|---|---|
| author | Fang, Xingli Li, Jianwei Mulchandani, Varun Kim, Jung-Eun |
| author_facet | Fang, Xingli Li, Jianwei Mulchandani, Varun Kim, Jung-Eun |
| contents | The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present promising insights and perspectives regarding concerns that challenge the trustworthiness of AI models. In particular, this paper investigates the issues regarding three thrusts: safety, privacy, and bias, which hurt models' trustworthiness. For safety, we discuss safety alignment in the context of large language models, preventing them from generating toxic or harmful content. For bias, we focus on spurious biases that can mislead a network. Lastly, for privacy, we cover membership inference attacks in deep neural networks. The discussions addressed in this paper reflect our own experiments and observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trustworthy AI: Safety, Bias, and Privacy -- A Survey Fang, Xingli Li, Jianwei Mulchandani, Varun Kim, Jung-Eun Cryptography and Security Artificial Intelligence Computation and Language Machine Learning The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present promising insights and perspectives regarding concerns that challenge the trustworthiness of AI models. In particular, this paper investigates the issues regarding three thrusts: safety, privacy, and bias, which hurt models' trustworthiness. For safety, we discuss safety alignment in the context of large language models, preventing them from generating toxic or harmful content. For bias, we focus on spurious biases that can mislead a network. Lastly, for privacy, we cover membership inference attacks in deep neural networks. The discussions addressed in this paper reflect our own experiments and observations. |
| title | Trustworthy AI: Safety, Bias, and Privacy -- A Survey |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2502.10450 |