# NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic

arXiv: https://arxiv.org/abs/2307.02849 · HTML: https://mlsanity.com/paper/2307.02849/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 88 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://mlsanity.com/paper/1804.06059/) (2018)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Contextualized Perturbation for Textual Adversarial Attack](https://mlsanity.com/paper/2009.07502/) (2020)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Semantics-aware BERT for Language Understanding](https://mlsanity.com/paper/1909.02209/) (2019)
- [Deep Text Classification Can be Fooled](https://mlsanity.com/paper/1704.08006/) (2017)
- [OpenAttack: An Open-source Textual Adversarial Attack Toolkit](https://mlsanity.com/paper/2009.09191/) (2020)
- [Interpretable Adversarial Perturbation in Input Embedding Space for Text](https://mlsanity.com/paper/1805.02917/) (2018)
- [Probing Natural Language Inference Models through Semantic Fragments](https://mlsanity.com/paper/1909.07521/) (2019)
- [Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations](https://mlsanity.com/paper/2002.04599/) (2020)
- [Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data](https://mlsanity.com/paper/2009.09139/) (2020)
- [Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference](https://mlsanity.com/paper/1907.04380/) (2019)
- [Generating Fluent Adversarial Examples for Natural Languages](https://mlsanity.com/paper/2007.06174/) (2020)

## Built on by (most cited first, 3 of 3)

- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection](https://mlsanity.com/paper/2501.02020/) (2025)
- [Explanation Generation for Contradiction Reconciliation with LLMs](https://mlsanity.com/paper/2603.22735/) (2026)

## Abstract (arXiv)

Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natural language inference. However, it remains an open question whether the models perform real reasoning to reach their conclusions or rely on spurious correlations. Adversarial attacks have proven to be an important tool to help evaluate the Achilles' heel of the victim models. In this study, we explore the fundamental problem of developing attack models based on logic formalism. We propose NatLogAttack to perform systematic attacks centring around natural logic, a classical logic formalism that is traceable back to Aristotle's syllogism and has been closely developed for natural language inference. The proposed framework renders both label-preserving and label-flipping attacks. We show that compared to the existing attack models, NatLogAttack generates better adversarial examples with fewer visits to the victim models. The victim models are found to be more vulnerable under the label-flipping setting. NatLogAttack provides a tool to probe the existing and future NLI models' capacity from a key viewpoint and we hope more logic-based attacks will be further explored for understanding the desired property of reasoning.