Vulnerabilities in ai code generators: Exploring targeted data poisoning attacks

D Cotroneo, C Improta, P Liguori… - Proceedings of the 32nd …, 2024 - dl.acm.org
AI-based code generators have become pivotal in assisting developers in writing software
starting from natural language (NL). However, they are trained on large amounts of data …

Adversarial training lattice LSTM for named entity recognition of rail fault texts

S Su, J Qu, Y Cao, R Li, G Wang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Learning and identifying key concepts from past fault records are essential for us to
understand the causes of these faults, which lay the foundation for the fault diagnosis and …

[HTML][HTML] Who evaluates the evaluators? On automatic metrics for assessing AI-based offensive code generators

P Liguori, C Improta, R Natella, B Cukic… - Expert Systems with …, 2023 - Elsevier
AI-based code generators are an emerging solution for automatically writing programs
starting from descriptions in natural language, by using deep neural networks (Neural …

[HTML][HTML] Automating the correctness assessment of AI-generated code for security contexts

D Cotroneo, A Foggia, C Improta, P Liguori… - Journal of Systems and …, 2024 - Elsevier
Evaluating the correctness of code generated by AI is a challenging open problem. In this
paper, we propose a fully automated method, named ACCA, to evaluate the correctness of …

End-to-end entity-aware neural machine translation

S **e, Y **a, L Wu, Y Huang, Y Fan, T Qin - Machine Learning, 2022 - Springer
Accurate translation of entities (eg, person names, organizations, geography) is important in
neural machine translation (briefly, NMT), as they are usually more difficult to translate than …

Challenges in context-aware neural machine translation

L **, J He, J May, X Ma - arxiv preprint arxiv:2305.13751, 2023 - arxiv.org
Context-aware neural machine translation involves leveraging information beyond sentence-
level context to resolve inter-sentential discourse dependencies and improve document …

DEEP: denoising entity pre-training for neural machine translation

J Hu, H Hayashi, K Cho, G Neubig - arxiv preprint arxiv:2111.07393, 2021 - arxiv.org
It has been shown that machine translation models usually generate poor translations for
named entities that are infrequent in the training corpus. Earlier named entity translation …

Extract and attend: Improving entity translation in neural machine translation

Z Zeng, R Wang, Y Leng, J Guo, X Tan, T Qin… - arxiv preprint arxiv …, 2023 - arxiv.org
While Neural Machine Translation (NMT) has achieved great progress in recent years, it still
suffers from inaccurate translation of entities (eg, person/organization name, location), due …

Neural machine translation for low-resource languages from a chinese-centric perspective: A survey

J Zhang, K Su, H Li, J Mao, Y Tian, F Wen… - ACM Transactions on …, 2024 - dl.acm.org
Machine translation–the automatic transformation of one natural language (source
language) into another (target language) through computational means–occupies a central …