لطفا منتظر بمانید ...
0% Complete
English
صفحه اصلی
/
شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Robustness Gap in NLP Models for Vulnerability Descriptions: Benchmarking and Data Augmentation
نویسندگان :
AmirHossein Majd
1
Mahdi Yousefikia
2
Saghar Ghasemzadeh
3
Amirreza Asari
4
Arya Khoshnavataher
5
Seyedeh Leili Mirtaheri
6
1- University of Calabria
2- دانشگاه خوارزمی
3- دانشگاه خوارزمی
4- دانشگاه خوارزمی
5- دانشگاه خوارزمی
6- University of Calabria
کلمات کلیدی :
Software Vulnerabilities،Natural Language Processing،Robustness Benchmark،Noise Injection،Exploitability Prediction،Data Augmentation،Cybersecurity
چکیده :
Software vulnerability descriptions from CVE/NVD are the primary corpus for analysis, prioritization, and risk management in cybersecurity. Yet natural noise (typos, synonym substitutions, lexical variety) and adversarial perturbations undermine the accuracy and trustworthiness of NLP models. This paper presents, to our knowledge, the first systematic benchmark of NLP robustness on vulnerability descriptions. We train nine diverse architectures—lightweight transformers (MiniLM, MPNet, SBERT), hybrid models (BERT-LSTM, TextRCNN), and classical recurrent networks (BiLSTM, LSTM)—on a balanced dataset of over 56,000 real-world records from NVD and Exploit-DB, and fine-tune them for exploitability prediction. For comprehensive evaluation, we inject three noise families into test sets at levels from 10% to 80%: character-level edits (substitutions/swaps), synonym replacements using WordNet, and composite adversarial attacks generated with TextAttack. Performance declines across all models as noise rises, but vulnerability profiles differ: MiniLM attains the strongest clean-data score (F1 ≈ 0.933) yet is most brittle under character noise, whereas TextRCNN, despite a lower baseline, preserves comparatively higher stability in heavily perturbed conditions. Finally, we test a pragmatic hardening strategy—data augmentation with noisy variants followed by retraining—which consistently narrows robustness gaps across architectures without materially sacrificing clean-data accuracy. The benchmark and code enable reproducible evaluation and future robust modeling in cybersecurity.
لیست مقالات
لیست مقالات بایگانی شده
Enhancing Employee Promotion Prediction with a Novel Hybrid Model Integrating Convolutional Neural Networks and Random Forest
Pouya Ardehkhani - Seyyed Reza Moslemi - Hanieh Hooshmand
Epileptic Seizure Detection based on Statistical and Wavelet Features and Siamese Network
Zahra Hossein-Nejad - Mehdi Nasri
Multi-label Classification of Steel Surface Defects Using Transfer Learning and Vision Transformer
Amirhossein Komijani - Farzaneh Vafaeinezhad - Javad Khoramdel - Yasamin Borhani - Esmaeil Najafi
روشی برای تشخیص مرحله پیشرفت آلزایمر در تصاویرFMRI مبتنی بر شبکه های عصبی چگال
فرساد زمانی بروجنی - عباس بهره دار
SBST challenges from the perspective of the test techniques
Sepideh Kashefi Gargari - Dr Mohammad Reza Keyvanpour
A Data-Efficient Approach to Solar Panel Micro-Crack Detection via Self-Supervised Learning
Alireza Akhavan safaei - Pegah Saboori - Reza Ramezani - Morteza Tavana
Dealing with Black-hole Attacks in Inter-vehicle Networks Using the Packet Delivery Rate Algorithm
Marzieh Sedighi - Mehdi Hamidkhani - Mostafa Sadeghi
A method for image steganography based on chaotic maps and advanced compression algorithms
Mohammad Yousefi Sorkhi
Classification of Personality Traits on Facebook Using Key Phrase Extraction, Language Models and Machine Learning
Faezeh Safari - Abdolah Chalechale
A New Method Based on Deep Learning and Time Stabilization of the Propagation Path for Fake News Detection
Fatemeh Torgheh - Dr Mohammad Reza Keyvanpour - Dr Behrooz Masoumi
بیشتر
ثمین همایش، سامانه مدیریت همایش ها و جشنواره ها - نگارش 45.0.1