Jul 2026· International Journal of Grid Computing & Applications· Vol 17, pp. 25-34· 0 citations· 6 references
TL;DR
Investigation of the effectiveness and adversarial robustness of two NLP classification approaches: a traditional TF-IDF Logistic Regression model and a transformer-based Bidirectional Encoder Representations from Transformers model demonstrate the advantages of transformer-based architectures for cybersecurity-oriented content moderation systems operating in adversarial online environments.
Abstract
The increasing prevalence of toxic online content has created significant challenges for digital platforms, necessitating the development of automated and robust toxic comment detection systems. Traditional Natural Language Processing (NLP) approaches based on statistical text representations often achieve strong baseline classification performance but remain vulnerable to adversarial text obfuscation techniques designed to evade content moderation systems. This research investigates the effectiveness and adversarial robustness of two NLP classification approaches: a traditional TF-IDF Logistic Regression model and a transformer-based Bidirectional Encoder Representations from Transformers (BERT) model. Using the Jigsaw Toxic Comment Classification dataset, the problem was simplified into binary toxic versus non-toxic classification. To evaluate robustness, adversarial augmentations including leetspeak substitution, character deletion, and spacing attacks were applied to toxic comments. Experimental results demonstrated that the BERT model significantly outperformed the Logistic Regression baseline in both standard classification performance and resilience against adversarial perturbations. While the Logistic Regression model experienced substantial performance degradation due to its dependence on exact lexical matching, the BERT model maintained strong performance through contextual embeddings and subword tokenization mechanisms. Among the evaluated attacks, substitution based obfuscation produced the greatest reduction in transformer performance, indicating that adversarial NLP remains an ongoing research challenge. The findings highlight the limitations of traditional bag-of-words approaches and demonstrate the advantages of transformer-based architectures for cybersecurity-oriented content moderation systems operating in adversarial online environments.
This paper explores the application of natural language processing and machine learning techniques to automatically detect and classify fake news articles and develops a web-based application to integrate the trained models into an interactive platform.
Vlad-Constantin Cristescu, Stelian Spinu· Journal of Military Technolo...· 0 citations
This study investigates response-only adversarial classification of LLM outputs through a comparative evaluation of lexical, contrastive, and contextual representations and provides a realistic benchmark for response-only adversarial detection and clarify the limits of contrastive representations when prompt information is absent.
A. Nasution, Ahmet Emre Ergün, Aytu˘g Onan et al.· IEEE Access· 0 citations
It is demonstrated that clean-text performance is not a reliable predictor of adversarial robustness, and the results underscore the necessity for architecture-specific defences and frame smishing detection as an adversarial cybersecurity challenge rather than a static classification task.
Denzel Chiuseni, A. Bahizire, Silva Hama et al.· 0 citations
Drug-related criminal activities on social media increasingly employ rapidly evolving coded languages, including fruit substitutions, numeric homophones, and dialectal metaphors, to evade detection. This adversarial obfuscation causes large-scale deep learning models to suffer from severe computational overhead during edge deployment, while reducing their robustness against evolving coded expressions. To mitigate these challenges, we construct a dedicated dataset containing 10,000 drug-related coded text samples and propose an optimized, lightweight TextCNN-based framework. The framework normalizes lexical variants of codewords using a domain-specific dictionary and adaptive normalization functions, and extracts local semantic patterns from the word embedding layer through multi-scale convolutional kernels (h∈{3,4,5}) to capture crucial short-text semantics in parallel. Experimental results demonstrate that the proposed framework achieves an F1 score of 99.3% with only 0.22 M parameters, significantly outperforming baseline models. These findings indicate that models optimized for local n-gram patterns provide a highly cost-effective deployment solution while outperforming representative pre-trained language models in specialized adversarial digital forensics tasks.
Tao Leng, Yong Dai, Xinyang Yan· Electronics· 0 citations
Phishing classifiers trained on static data can underperform when slight adversarial modifications are made to URLs and HTML to evade both humans and traditional machine learning algorithms. During this research, a published XGBoost baseline from Aljofey et al. was reproduced and verified for reproducibility with multi-seed evaluation. The reproduced model attained a 94.76% accuracy, 92.19% F1, and 98.40% AUC with low seed variance on the clean data. To quantify adversarial vulnerability, homoglyph substitutions, zero-width character injections, and benign keyword padding were used. These adversarial modifications reduced phishing recall from 90.96% to 75.34%, a decrease of 15.62 percentage points (pp). To combat this, a DDQN preprocessor that learns to apply minimal, deterministic “repair” actions before the frozen XGBoost classifier was developed. On a mixed-label adversarial test, the DDQN+XGBoost improved F1 by +10.08 pp and accuracy by +9.65 pp versus the adversarial baseline, cuts FPR by -16.68 pp (60.35% relative), and maintains high recall (-3.12 pp trade-off). The defence requires no retraining of the base classifier, is interpretable at the action level, and adds modest inference overhead. These results demonstrate that learned preprocessing can restore deployable performance in the face of targeted adversarial attacks. This research shows that learned preprocessing can enhance adversarial defence for phishing detection at inference time, without changing the underlying classifier.
Deep neural networks (DNNs) are vulnerable to adversarial attacks, which can cause security risks in computer information systems. Feature disruption attacks, as a typical form of adversarial attack, optimize adversarial examples by disrupting the intermediate features extracted by DNN. The existing feature disruption attacks have limitations when it comes to objects of different scales within resolution features, favoring low-resolution feature maps and low-scoring objects. The imbalance above affects their effectiveness in object detection tasks. Gradient-guided Hierarchical Feature Attack (GHFA) is proposed to solve these problems, which disrupts detector-extracted features using gradient-guided feature weighting. GHFA incorporates receptive field scaling and gradient scaling to balance the focus among feature maps and enhance attack performance. The evaluation of GHFA on 9 object detectors demonstrates its superior transferability compared with the 6 comparative methods, surpassing the second-ranked method by 2.4%. Furthermore, the real-world applicability of GHFA is validated available by testing it on a commercial online object detection platform.
Yang Wang, Yunfei Zheng, Lei Chen et al.· Journal of King Saud Univers...· 3 citations