born in 1982. PhD candidate. Member of CCF. His main research interests include data-driven security and privacy, and AI security
born in 1996. PhD candidate. Member of CCF. His main research interest includes AI security and privacy
born in 1993. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computational photography, deep feature fusion interpretability of neural networks, adversarial training
born in 1992. PhD, associate professor. Member of CCF. His main research interests include equipment information security and AI security
born in 1989. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network and information security, AI security, and large language model security
born in 1976. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include cyberspace and system security, and blockchain and privacy preservation
born in 1982. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include cryptography and security protocols, big data security, and privacy protection
born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interest includes visual analytics
born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics
In recent years, large language models (LLMs) have emerged as a critical branch of deep learning network technology, achieving a series of breakthrough accomplishments in the field of natural language processing (NLP), and gaining widespread adoption. However, throughout their entire lifecycle, including pre-training, fine-tuning, and actual deployment, a variety of security threats and risks of privacy breaches have been discovered, drawing increasing attention from both the academic and industrial sectors. Navigating the development of the paradigm of using large language models to handle natural language processing tasks, as known as the pre-training and fine-tuning paradigm, the pre-training and prompt learning paradigm, and the pre-training and instruction-tuning paradigm, this article outlines conventional security threats against large language models, specifically representative studies on the three types of traditional adversarial attacks (adversarial example attack, backdoor attack and poisoning attack). It then summarizes some of the novel security threats revealed by recent research, followed by a discussion on the privacy risks of large language models and the progress in their research. The content aids researchers and deployers of large language models in identifying, preventing, and mitigating these threats and risks during the model design, training, and application processes, while also achieving a balance between model performance, security, and privacy protection.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |