# ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations

arXiv: https://arxiv.org/abs/2603.14843 · HTML: https://mlsanity.com/paper/2603.14843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 70 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 30 of 34)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Less-forgetting Learning in Deep Neural Networks](https://mlsanity.com/paper/1607.00122/) (2016)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Essentials for Class Incremental Learning](https://mlsanity.com/paper/2102.09517/) (2021)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate](https://mlsanity.com/paper/2108.05921/) (2021)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [Multi-Domain Incremental Learning for Semantic Segmentation](https://mlsanity.com/paper/2110.12205/) (2021)
- [Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection](https://mlsanity.com/paper/2402.11406/) (2024)
- [Towards Robust Toxic Content Classification](https://mlsanity.com/paper/1912.06872/) (2019)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation](https://mlsanity.com/paper/2410.22658/) (2024)
- [Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning](https://mlsanity.com/paper/2410.00911/) (2024)
- [Towards Building a Robust Toxicity Predictor](https://mlsanity.com/paper/2404.08690/) (2024)
- [In Defense of the Learning Without Forgetting for Task Incremental Learning](https://mlsanity.com/paper/2107.12304/) (2021)
- [Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense](https://mlsanity.com/paper/2203.10346/) (2022)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [Improving Continual Relation Extraction by Distinguishing Analogous Semantics](https://mlsanity.com/paper/2305.06620/) (2023)

## Abstract (arXiv)

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop evasive perturbations to disguise toxic content and evade detectors. Traditional detectors or methods are static over time and are inadequate in addressing these evolving evasion tactics. Thus, continual learning emerges as a logical approach to dynamically update detection ability against evolving perturbations. Nevertheless, disparities across perturbations hinder the detector's continual learning on perturbed text. More importantly, perturbation-induced noises distort semantics to degrade comprehension and also impair critical feature learning to render detection sensitive to perturbations. These amplify the challenge of continual learning against evolving perturbations. In this work, we present ContiGuard, the first framework tailored for continual learning of the detector on time-evolving perturbed text (termed continual toxicity detection) to enable the detector to continually update capability and maintain sustained resilience against evolving perturbations. Specifically, to boost the comprehension, we present an LLM-powered semantic enriching strategy, where we dynamically incorporate possible meaning and toxicity-related clues excavated by LLM into the perturbed text to improve the comprehension. To mitigate non-critical features and amplify critical ones, we propose a discriminability-driven feature learning strategy, where we strengthen discriminative features while suppressing the less-discriminative ones to shape a robust classification boundary for detection...