Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification

• URL: http://arxiv.org/abs/2307.01225v3
• Date: Fri, 24 Oct 2025 02:56:33 GMT
• Title: Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification
• Authors: Bushra Sabir, Yansong Gao, Alsharif Abuadbba, M. Ali Babar,
• Abstract summary: This paper presents a unified framework called Explainability-driven Detection, Identification, and Transformation (EDIT) to strengthen inference-time defenses.<n>EDIT integrates explainability tools, including attention maps and integrated gradients, with frequency-based features to automatically detect and identify adversarial perturbations.<n>The framework provides robust, interpretable, and efficient protection against both standard, zero-day, and adaptive adversarial threats in text classification models.
• Score: 9.818997495801705
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security concerns, as small input perturbations can cause severe misclassifications. Existing robustness methods often require heavy computation or lack interpretability. This paper presents a unified framework called Explainability-driven Detection, Identification, and Transformation (EDIT) to strengthen inference-time defenses. EDIT integrates explainability tools, including attention maps and integrated gradients, with frequency-based features to automatically detect and identify adversarial perturbations while offering insight into model behavior. After detection, EDIT refines adversarial inputs using an optimal transformation process that leverages pre-trained embeddings and model feedback to replace corrupted tokens. To enhance security assurance, EDIT incorporates automated alerting mechanisms that involve human analysts when necessary. Beyond static defenses, EDIT also provides adaptive resilience by enforcing internal feature similarity and transforming inputs, thereby disrupting the attackers optimization process and limiting the effectiveness of adaptive adversarial attacks. Experiments using BERT and RoBERTa on IMDB, YELP, AGNEWS, and SST2 datasets against seven word substitution attacks demonstrate that EDIT achieves an average Fscore of 89.69 percent and balanced accuracy of 89.70 percent. Compared to four state-of-the-art defenses, EDIT improves balanced accuracy by 1.22 times and F1-score by 1.33 times while being 83 times faster in feature extraction. The framework provides robust, interpretable, and efficient protection against both standard, zero-day, and adaptive adversarial threats in text classification models.

Related papers

• ThreatFormer-IDS: Robust Transformer Intrusion Detection with Zero-Day Generalization and Explainable Attribution [0.0]
  Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels.<n>We propose ThreatFormer- IDS, a Transformer-based sequence modeling framework that converts flow records into time-ordered windows and learns contextual representations for robust intrusion screening.<n>On the ToN IoT benchmark with chronological evaluation, ThreatFormer-IDS achieves AUCROC 0.994, AUC-PR 0.956, and Recall@1%FPR 0.910, outperforming strong tree-based and sequence baselines.
  arXiv  Detail & Related papers  (2026-02-26T23:20:42Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• Vision Transformers: the threat of realistic adversarial patches [48.03238826812818]
  Vision Transformers (ViTs) have gained significant traction in modern machine learning.<n>ViTs remain vulnerable to evasion attacks, particularly to adversarial patches.<n>This study investigates the transferability of adversarial attack techniques used in CNNs when applied to ViT classification models.
  arXiv  Detail & Related papers  (2025-09-25T12:36:25Z)
• Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations [2.7620215077666557]
  Modern detectors are notoriously vulnerable to adversarial attacks, with paraphrasing standing out as an effective evasion technique.<n>This paper presents a comparative study of adversarial robustness, first by quantifying the limitations of standard adversarial training.<n>We then introduce a novel, significantly more resilient detection framework: Perturbation-Invariant Feature Engineering.
  arXiv  Detail & Related papers  (2025-09-22T13:03:53Z)
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers [0.0]
  Large language models (LLMs) aligned for safety often exhibit emergent deceptive behaviors.<n>This paper introduces adversarial activation patching, a novel mechanistic interpretability framework.<n>By sourcing activations from "deceptive" prompts, we simulate vulnerabilities and quantify deception rates.
  arXiv  Detail & Related papers  (2025-07-12T21:29:49Z)
• On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning [0.0]
  We investigate the role of adversarial data augmentation (ADA) in enhancing both robustness and adaptivity in transfer learning settings.<n>We propose a unified framework that integrates ADA with consistency regularization and domain-invariant representation learning.<n>Our results highlight a constructive perspective of adversarial learning, transforming perturbation from a destructive attack into a regularizing force for cross-domain transferability.
  arXiv  Detail & Related papers  (2025-05-19T03:56:51Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack [51.16384207202798]
  Vision-language pre-training models are vulnerable to multimodal adversarial examples (AEs) Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process. We propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity.
  arXiv  Detail & Related papers  (2024-11-04T23:07:51Z)
• Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding [118.75567341513897]
  Existing methods typically analyze target text in isolation or solely with non-member contexts. We propose Con-ReCall, a novel approach that leverages the asymmetric distributional shifts induced by member and non-member contexts.
  arXiv  Detail & Related papers  (2024-09-05T09:10:38Z)
• Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods [0.0]
  A text adversarial attack involves the deliberate manipulation of input text to mislead the predictions of the model. BERT, BERT-on-BERT attack, and Fraud Bargain's Attack (FBA) are explored in this paper. PWWS emerges as the most potent adversary, consistently outperforming other methods across multiple evaluation scenarios.
  arXiv  Detail & Related papers  (2024-04-08T02:55:01Z)
• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• Adaptive Attack Detection in Text Classification: Leveraging Space Exploration Features for Text Sentiment Classification [44.99833362998488]
  Adversarial example detection plays a vital role in adaptive cyber defense, especially in the face of rapidly evolving attacks. We propose a novel approach that leverages the power of BERT (Bidirectional Representations from Transformers) and introduces the concept of Space Exploration Features.
  arXiv  Detail & Related papers  (2023-08-29T23:02:26Z)
• Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation [66.33340583035374]
  We present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation. We demonstrate that 6 state-of-the-art text-based adversarial attacks do not maintain their efficacy after round-trip translation. We introduce an intervention-based solution to this problem, by integrating Machine Translation into the process of adversarial example generation.
  arXiv  Detail & Related papers  (2023-07-24T04:29:43Z)
• In and Out-of-Domain Text Adversarial Robustness via Label Smoothing [64.66809713499576]
  We study the adversarial robustness provided by various label smoothing strategies in foundational models for diverse NLP tasks. Our experiments show that label smoothing significantly improves adversarial robustness in pre-trained models like BERT, against various popular attacks. We also analyze the relationship between prediction confidence and robustness, showing that label smoothing reduces over-confident errors on adversarial examples.
  arXiv  Detail & Related papers  (2022-12-20T14:06:50Z)
• Estimating the Adversarial Robustness of Attributions in Text with Transformers [44.745873282080346]
  We establish a novel definition of attribution robustness (AR) in text classification, based on Lipschitz continuity. We then propose our novel TransformerExplanationAttack (TEA), a strong adversary that provides a tight estimation for attribution in text classification.
  arXiv  Detail & Related papers  (2022-12-18T20:18:59Z)
• Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning [80.21709045433096]
  A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample. We use metric learning to frame adversarial regularization as an optimal transport problem. Our preliminary results indicate that regularizing over invariant perturbations in our framework improves both invariant and sensitivity defense.
  arXiv  Detail & Related papers  (2022-11-04T13:54:02Z)
• Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness [17.5771010094384]
  Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. Recent work argues the adversarial vulnerability of the model is caused by the non-robust features in supervised training. In this paper, we tackle the adversarial challenge from the view of disentangled representation learning.
  arXiv  Detail & Related papers  (2022-10-26T18:14:39Z)
• Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations [2.543865489517869]
  This work motivates textual counterfactuals by laying the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Experiments on sentiment analysis data show that the connectedness of counterfactuals to their original counterparts is not obvious in both models.
  arXiv  Detail & Related papers  (2022-10-17T09:50:02Z)
• Semantically Distributed Robust Optimization for Vision-and-Language Inference [34.83271008148651]
  We present textbfSDRO, a model-agnostic method that utilizes a set linguistic transformations in a distributed robust optimization setting. Experiments on benchmark datasets with images and video demonstrate performance improvements as well as robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2021-10-14T06:02:46Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.