Adversarial Machine Learning in the Context of Network Security: Challenges and Solutions

M Khan, L Ghafoor - Journal of Computational Intelligence …, 2024 - thesciencebrigade.com
With the increasing sophistication of cyber threats, the integration of machine learning (ML)
techniques in network security has become imperative for detecting and mitigating evolving …

Error analysis prompting enables human-like translation evaluation in large language models: A case study on chatgpt

Q Lu, B Qiu, L Ding, L Xie, D Tao - 2023 - preprints.org
Generative large language models (LLMs), eg, ChatGPT, have demonstrated remarkable
proficiency across several NLP tasks such as machine translation, question answering, text …

Learning graph neural networks for image style transfer

Y Jing, Y Mao, Y Yang, Y Zhan, M Song… - … on Computer Vision, 2022 - Springer
State-of-the-art parametric and non-parametric style transfer approaches are prone to either
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …

A survey on non-autoregressive generation for neural machine translation and beyond

Y Xiao, L Wu, J Guo, J Li, M Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …

Redistributing low-frequency words: Making the most of monolingual data in non-autoregressive translation

L Ding, L Wang, S Shi, D Tao, Z Tu - … of the 60th Annual Meeting of …, 2022 - aclanthology.org
Abstract Knowledge distillation (KD) is the preliminary step for training non-autoregressive
translation (NAT) models, which eases the training of NAT models at the cost of losing …

Token-level self-evolution training for sequence-to-sequence learning

K Peng, L Ding, Q Zhong, Y Ouyang… - Proceedings of the …, 2023 - aclanthology.org
Adaptive training approaches, widely used in sequence-to-sequence models, commonly
reweigh the losses of different target tokens based on priors, eg word frequency. However …

Directed acyclic transformer for non-autoregressive machine translation

F Huang, H Zhou, Y Liu, H Li… - … Conference on Machine …, 2022 - proceedings.mlr.press
Abstract Non-autoregressive Transformers (NATs) significantly reduce the decoding latency
by generating all tokens in parallel. However, such independent predictions prevent NATs …

Order-agnostic cross entropy for non-autoregressive machine translation

C Du, Z Tu, J Jiang - International conference on machine …, 2021 - proceedings.mlr.press
We propose a new training objective named order-agnostic cross entropy (OaXE) for fully
non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy …

Quantum Computing and AI in the Cloud

H Padmanaban - Journal of Computational Intelligence and …, 2024 - thesciencebrigade.com
The intersection of quantum computing and artificial intelligence (AI) within the cloud
environment represents a paradigm shift in the capabilities of computational technologies …

Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction

Z Xu, K Peng, L Ding, D Tao, X Lu - arXiv preprint arXiv:2403.09963, 2024 - arxiv.org
Recent research shows that pre-trained language models (PLMs) suffer from" prompt bias"
in factual knowledge extraction, ie, prompts tend to introduce biases toward specific labels …