[HTML][HTML] A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Y Yao, J Duan, K Xu, Y Cai, Z Sun, Y Zhang - High-Confidence Computing, 2024 - Elsevier
Abstract Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized
natural language understanding and generation. They possess deep language …

A survey of adversarial defenses and robustness in nlp

S Goyal, S Doddapaneni, MM Khapra… - ACM Computing …, 2023 - dl.acm.org
In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

[HTML][HTML] Pre-trained models: Past, present and future

X Han, Z Zhang, N Ding, Y Gu, X Liu, Y Huo, J Qiu… - AI Open, 2021 - Elsevier
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Cline: Contrastive learning with semantic negative examples for natural language understanding

D Wang, N Ding, P Li, HT Zheng - arXiv preprint arXiv:2107.00440, 2021 - arxiv.org
Despite pre-trained language models have proven useful for learning high-quality semantic
representations, these models are still vulnerable to simple perturbations. Recent works …

Black-box access is insufficient for rigorous ai audits

S Casper, C Ezell, C Siegmann, N Kolt… - The 2024 ACM …, 2024 - dl.acm.org
External audits of AI systems are increasingly recognized as a key mechanism for AI
governance. The effectiveness of an audit, however, depends on the degree of access …

A review of semi-supervised learning for text classification

JM Duarte, L Berton - Artificial intelligence review, 2023 - Springer
A huge amount of data is generated daily leading to big data challenges. One of them is
related to text mining, especially text classification. To perform this task we usually need a …

Adversarial attack and defense technologies in natural language processing: A survey

S Qiu, Q Liu, S Zhou, W Huang - Neurocomputing, 2022 - Elsevier
Recently, the adversarial attack and defense technology has made remarkable
achievements and has been widely applied in the computer vision field, promoting its rapid …

Better robustness by more coverage: Adversarial training with mixup augmentation for robust fine-tuning

C Si, Z Zhang, F Qi, Z Liu, Y Wang, Q Liu… - arXiv preprint arXiv …, 2020 - arxiv.org
Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve
the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted …

Searching for an effective defender: Benchmarking defense against adversarial word substitution

Z Li, J Xu, J Zeng, L Li, X Zheng, Q Zhang… - arXiv preprint arXiv …, 2021 - arxiv.org
Recent studies have shown that deep neural networks are vulnerable to intentionally crafted
adversarial examples, and various methods have been proposed to defend against …

Flooding-X: Improving BERT's resistance to adversarial attacks via loss-restricted fine-tuning

Q Liu, R Zheng, B Rong, J Liu, Z Liu… - Proceedings of the …, 2022 - aclanthology.org
Adversarial robustness has attracted much attention recently, and the mainstream solution is
adversarial training. However, the tradition of generating adversarial perturbations for each …