Research map / Adversarial robustness and security / Attacks on text and graphs
Fooling Explanations in Text Classifiers
Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use TEF's attribution-guided word ranking and best-synonym selection instead of RandomAttack's random choices | TextExplanationFooler (TEF) · Five text-classification datasets, tested across the reported models and explainers | attribution correlation | Improved |
| Randomize the word-importance ranking while retaining best-synonym selection (ablation) | TEF · Text-classification datasets and models in the ablation study | PCC | Hurt |
| Randomize final synonym selection while retaining word-importance ranking (ablation) | TEF · Text-classification datasets and models in the ablation study | PCC | Improved |
| Transfer TEF perturbations from another model or explanation method rather than optimize them on the target | TEF · Text-classification models and explanation methods | PCC: approx. 0.4 | Mixed |
| Apply precomputed semi-universal replacement policies without querying the target during attack time | TEF · Text-classification models and explanation methods | PCC | Improved |
| Increase the maximum perturbed-token ratio | TEF · Text-classification datasets and models | attribution correlation | Improved |
Closest papers by meaning
- Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction (AAAI 2022 · similarity 0.87)
- Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment (AAAI 2020 · similarity 0.86)
- A General Search-Based Framework for Generating Textual Counterfactual Explanations (AAAI 2024 · similarity 0.86)
- Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space (CVPR 2023 · similarity 0.86)
- NOMATTERXAI: Generating “No Matter What” Alterfactual Examples for Explaining Black-Box Text Classification Models (AAAI 2025 · similarity 0.85)
- Accelerating the Global Aggregation of Local Explanations (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
