Ulteriori informazioni
This book offers an extensive exploration of foundation models, guiding readers through the essential concepts and advanced topics that define this rapidly evolving research area. Designed for those seeking to deepen their understanding and contribute to the development of safer and more trustworthy AI technologies, the book is divided into three parts providing the fundamentals, advanced topics in foundation modes, and safety and trust in foundation models:
- Part I introduces the core principles of foundation models and generative AI, presents the technical background of neural networks, delves into the learning and generalization of transformers, and finishes with the intricacies of transformers and in-context learning.
- Part II introduces automated visual prompting techniques, prompting LLMs with privacy, memory-efficient fine-tuning methods, and shows how LLMs can be reprogrammed for time-series machine learning tasks. It explores how LLMs can be reused for speech tasks, how synthetic datasets can be used to benchmark foundation models, and elucidates machine unlearning for foundation models.
- Part III provides a comprehensive evaluation of the trustworthiness of LLMs, introduces jailbreak attacks and defenses for LLMs, presents safety risks when find-tuning LLMs, introduces watermarking techniques for LLMs, presents robust detection of AI-generated text, elucidates backdoor risks in diffusion models, and presents red-teaming methods for diffusion models.
Mathematical notations are clearly defined and explained throughout, making this book an invaluable resource for both newcomers and seasoned researchers in the field.
Sommario
Part I-Fundamentals of Foundation Models.-Chapter 1-Foundation Models and Generative AI.- Chapter 2-Neural Networks.- Chapter 3- Learning and Generalization of Vision Transformers.- Chapter 4-Formalizing In-Context Learning in Transformers.- Part II Advanced Topics in Foundation Model.- Chapter 5-Automated Visual Prompting.- Chapter 6-Prompting Large Language Models with Privacy.- Chapter 7- Memory-Efficient Fine-Tuning for Foundation Models.- Chapter 8 Large Language Models Meet Time Series.- Chapter 9-Large Language Models Meet Speech Recognition.- Chapter 10-Benchmarking Foundation Models using Synthetic Datasets.- Chapter 11-Machine Unlearning for Foundation Models.- Chapter 12-Part III Trust and Safety in Foundation Models.- Chapter 12-Trustworthiness Evaluation of Large Language Models.- Chapter 13-Attacks and Defenses on Aligned Large Language Models.- Chapter 14- Safety Risks in Fine-tuning Large Language Models.- Chapter15- Watermarks for Large Language Models.- Chapter 16- AI-Generated Text Detection.- Chapter 17- Backdoor Risks in Diffusion Models.- Chapter 18- Prompt Engineering for Safety Red-teaming: A Case Study on Text-to-Image Diffusion Models.
Info autore
Dr. Pin-Yu Chen is a principal research scientist at IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA. He is also the chief scientist of RPI-IBM AI Research Collaboration and PI of ongoing MIT-IBM Watson AI Lab projects. Dr. Chen received his Ph.D. in electrical engineering and computer science from the University of Michigan, Ann Arbor, USA, in 2016. Dr. Chen’s recent research focuses on adversarial machine learning of neural networks for robustness and safety. His long-term research vision is to build trustworthy machine learning systems. He received the IJCAI Computers and Thought Award in 2023. He also received the IEEE GLOBECOM 2010 GOLD Best Paper Award and UAI 2022 Best Paper Runner-Up Award. At IBM Research, he received several research accomplishment awards, including IBM Master Inventor, IBM Corporate Technical Award, and IBM Pat Goldberg Memorial Best Paper. He is a co-author of the book “Adversarial Robustness for Machine Learning”. He is currently on the editorial board of Transactions on Machine Learning Research and IEEE Transactions on Signal Processing. He is also an Area Chair of several AI and machine learning conferences, and a Distinguished Lecturer of ACM.
Dr. Sijia Liu is currently an Assistant Professor in the CSE department at Michigan State University and an Affiliated Professor at IBM Research. His primary research interests include trustworthy and scalable machine learning (ML), with a recent focus on machine unlearning. He has been recognized with several prestigious awards, including the NSF CAREER award in 2024, the Best Paper Runner-Up Award at the Conference on Uncertainty in Artificial Intelligence (UAI) in 2022, and the Best Student Paper Award at the 42nd IEEE ICASSP in 2017. He has published over 70 papers in top ML/AI conferences based on his record in CSRanking and co-organized several tutorials and workshops on trustworthy and scalable ML.
