# Not-in-Perspective: Towards Shielding Google's Perspective API Against Adversarial Negation Attacks

arXiv: https://arxiv.org/abs/2602.09343 · HTML: https://mlsanity.com/paper/2602.09343/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Deceiving Google's Perspective API Built for Detecting Toxic Comments](https://mlsanity.com/paper/1702.08138/) (2017)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [Shielding Google's language toxicity model against adversarial attacks](https://mlsanity.com/paper/1801.01828/) (2018)
- [Impact of Sentiment Detection to Recognize Toxic and Subversive Online Comments](https://mlsanity.com/paper/1812.01704/) (2018)

## Abstract (arXiv)

The rise of cyberbullying in social media platforms involving toxic comments has escalated the need for effective ways to monitor and moderate online interactions. Existing solutions of automated toxicity detection systems, are based on a machine or deep learning algorithms. However, statistics-based solutions are generally prone to adversarial attacks that contain logic based modifications such as negation in phrases and sentences. In that regard, we present a set of formal reasoning-based methodologies that wrap around existing machine learning toxicity detection systems. Acting as both pre-processing and post-processing steps, our formal reasoning wrapper helps alleviating the negation attack problems and significantly improves the accuracy and efficacy of toxicity scoring. We evaluate different variations of our wrapper on multiple machine learning models against a negation adversarial dataset. Experimental results highlight the improvement of hybrid (formal reasoning and machine-learning) methods against various purely statistical solutions.