diff --git a/MLLM_latex/chapter10/chap10_ref.bib b/MLLM_latex/chapter10/chap10_ref.bib
new file mode 100644
index 0000000..debb921
--- /dev/null
+++ b/MLLM_latex/chapter10/chap10_ref.bib
@@ -0,0 +1,115 @@
+@article{einstein,
+    author = "Albert Einstein",
+    title = "On the Electrodynamics of Moving Bodies",
+    journal = "Annalen der Physik",
+    year = "1905",
+    volume = "322",
+    pages = "891--921"
+}
+
+@article{konidena2024ethical,
+  title={Ethical Considerations in the Development and Deployment of AI Systems},
+  author={Konidena, Bhargav Kumar and Malaiyappan, Jesu Narkarunai Arasu and Tadimarri, Anish},
+  journal={European Journal of Technology},
+  volume={8},
+  number={2},
+  pages={41--53},
+  year={2024}
+}
+
+@article{peng2024securing,
+  title={Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks},
+  author={Peng, Benji and Chen, Keyu and Li, Ming and Feng, Pohsun and Bi, Ziqian and Liu, Junyu and Niu, Qian},
+  journal={arXiv preprint arXiv:2409.08087},
+  year={2024}
+}
+
+@article{boix2022machine,
+  title={Can machine-learning models overcome biased datasets?},
+  author={Boix, Xavier and Tenenbaum, Joshua B. and Torralba, Antonio},
+  journal={MIT News},
+  year={2022},
+  url={https://news.mit.edu/2022/machine-learning-biased-data-0221}
+}
+
+@misc{pymetrics2022audit,
+  title={audit-AI: Open Sourced Bias Testing for Generalized Machine Learning Applications},
+  author={pymetrics},
+  year={2022},
+  howpublished={\url{https://github.com/pymetrics/audit-ai}},
+  note={GitHub repository}
+}
+
+@inproceedings{kim2024domain,
+  title={Domain-Aware Fine-Tuning: Enhancing Neural Network Adaptability},
+  author={Seokhyeon Ha, Sunbeom Jung, Jungwoo Lee},
+  booktitle={Proceedings of the 38th AAAI Conference on Artificial Intelligence},
+  year={2024}
+}
+
+@article{zhang2023mitigating,
+  title={Bias-Aware Low-Rank Adaptation: Mitigating Catastrophic Inheritance of Large Language Models},
+  author={Zhang, Xingchen and Ren, Zhuosheng and Jiang, Yihong and Zhao, Dongyan and Zhang, Rui},
+  journal={arXiv preprint arXiv:2408.04556},
+  year={2023}
+}
+
+@article{aquino2023practical,
+  title={Practical, epistemic and normative implications of algorithmic bias in healthcare artificial intelligence: a qualitative study of multidisciplinary expert perspectives},
+  author={Aquino, Yves Saint James and Carter, Stacy M and Houssami, Nehmat and Braunack-Mayer, Annette and Win, Khin Than and Degeling, Chris and Wang, Lei and Rogers, Wendy A},
+  journal={Journal of Medical Ethics},
+  year={2023},
+  publisher={Institute of Medical Ethics}
+}
+
+@article{he2024emerged,
+  title={The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies},
+  author={He, Feng and Zhu, Tianqing and Ye, Dayong and Liu, Bo and Zhou, Wanlei and Yu, Philip S},
+  journal={arXiv preprint arXiv:2407.19354},
+  year={2024}
+}
+
+@article{friha2024llm,
+  title={LLM-Based Edge Intelligence: A Comprehensive Survey on Architectures, Applications, Security and Trustworthiness},
+  author={Friha, Othmane and Ferrag, Mohamed Amine and Kantarci, Burak and Cakmak, Burak and Ozgun, Arda and Ghoualmi-Zine, Nassira},
+  journal={IEEE Open Journal of the Communications Society},
+  year={2024},
+  publisher={IEEE}
+}
+
+@article{mccoy2023ethical,
+  title={Ethical responsibilities for companies that process personal data},
+  author={McCoy, Matthew S and Allen, Anita L and Kopp, Katharina and Mello, Michelle M and Patil, DJ and Ossorio, Pilar and Joffe, Steven and Emanuel, Ezekiel J},
+  journal={The American Journal of Bioethics},
+  volume={23},
+  number={11},
+  pages={11--23},
+  year={2023},
+  publisher={Taylor \& Francis}
+}
+
+@article{chen2024trustworthy,
+  title={Trustworthy, Responsible, and Safe AI: A Comprehensive Architectural Framework for AI Safety with Challenges and Mitigations},
+  author={Chen, Chen and Liu, Ziyao and Jiang, Weifeng and Qi, Goh Si and Lam, KwoK-Yan},
+  journal={arXiv preprint arXiv:2408.12935},
+  year={2024}
+}
+
+@article{ray2023chatgpt,
+  title={ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope},
+  author={Ray, Partha Pratim},
+  journal={Internet of Things and Cyber-Physical Systems},
+  volume={3},
+  pages={121--154},
+  year={2023},
+  publisher={Elsevier}
+}
+
+@incollection{rosenstrauch2023artificial,
+  title={Artificial Intelligence and Ethics},
+  author={Rosenstrauch, Doreen and Mangla, Utpal and Gupta, Atul and Masau, Costansia Taikwa},
+  booktitle={Digital Health Entrepreneurship},
+  pages={225--239},
+  year={2023},
+  publisher={Springer}
+}
\ No newline at end of file