Jul 2026· Journal of Intelligent Decision Making and Information Science· 0 citations· 19 references
TL;DR
This paper introduces a new anagram based attack into the literature and trains the model to learn these representations by adding a novel label to the dataset which is used as a feature for training the model.
Abstract
Natural Language Processing models are vulnerable to adversarial perturbations which can derail the model’s classification ability. Existing works focus on correcting the training data in order to be resilient to these attacks. In this paper, we propose the idea of multi label classification for adversarial attacks. First, we introduce a new anagram based attack into the literature and second, we train our model to learn these representations by adding a novel label to the dataset which is used as a feature for training the model. Our results show that our method succeeds in separating clean samples from adversarial ones without changing the actual data in the process. We conducted our experiments on the internet movie database dataset. Results show that our method makes a model reliable and robust against character-level perturbations.
This paper reveals that samples generated by a well-trained generative model are close to clean ones but far from adversarial ones, and proposes Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data.
Shuhai Zhang, Jiahao Yang, Hui Luo et al.· IEEE Transactions on Pattern...· 0 citations
A method to analyze ANNs designed for image classification from an adversarial robustness perspective and implemented an ablation and fine-tuning strategy that successfully boosted the robustness of the ANNs against a variant of the Auto-PGD attack under different threat models.
This work proposes AMRM-Pure, a purification framework that denoises adversarial inputs by preserving patch-level semantics, and formulate this process as a tractable optimization problem with respect to the input.
Zhihao Dou, Zhiqiang Gao, Dongfei Cui et al.· 0 citations
It is concluded that ordinary datasets can contain exploitable adversarial surfaces even in the absence of poisoning, and suggested that dataset audits should treat spurious structure not only as a source of bias or interpretability failure, but also as a latent attack surface for vision models.
Paul K. Mandal, Pavan Reddy, Tristan Malatynski· 0 citations
The proposed method improves classification accuracy on clean samples compared to the original IBD, while maintaining similar accuracy on adversarial samples, and is competitive with state-of-the-art approaches, including the recent dual-teacher distillation framework B-MTARD.
Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi et al.· 0 citations
Deep Neural Networks are vulnerable to adversarial perturbations, which can cause failures in safety-critical systems. State-of-the-art countermeasures often incur prohibitive overheads, creating a need for cost-efficient robustness strategies. This paper proposes a hybrid hardening technique integrating Triple Modular Redundancy with Adversarial Training, Label Smoothing, and Iterative Pruning to reduce hardening cost while preserving accuracy. Experimental results demonstrate that our approach maintains up to 86.7% accuracy under strong adversarial perturbations (ϵ = 0.1), outperforming unprotected models by a factor of 4.8x while reducing memory footprint up to 76% through pruning.
L. D. de Melo, M. Gani, Alberto Bosio et al.· IEEE International Symposium...· 0 citations
