# Generating Label Cohesive and Well-Formed Adversarial Claims

arXiv: https://arxiv.org/abs/2009.08205 · HTML: https://mlsanity.com/paper/2009.08205/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 27 of 27)

- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://mlsanity.com/paper/2103.00242/) (2021)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Generating Scientific Claims for Zero-Shot Scientific Fact Checking](https://mlsanity.com/paper/2203.12990/) (2022)
- [Synthetic Disinformation Attacks on Automated Fact Verification Systems](https://mlsanity.com/paper/2202.09381/) (2022)
- [Zero-shot Fact Verification by Claim Generation](https://mlsanity.com/paper/2105.14682/) (2021)
- [Efficient (Soft) Q-Learning for Text Generation with Limited Good Data](https://mlsanity.com/paper/2106.07704/) (2021)
- [Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking](https://mlsanity.com/paper/2502.09083/) (2025)
- [Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing](https://mlsanity.com/paper/2112.06924/) (2021)
- [Matching Tweets With Applicable Fact-Checks Across Languages](https://mlsanity.com/paper/2202.07094/) (2022)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems](https://mlsanity.com/paper/2209.03755/) (2022)
- [Fact Checking with Insufficient Evidence](https://mlsanity.com/paper/2204.02007/) (2022)
- [EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification](https://mlsanity.com/paper/2310.14508/) (2023)
- [Towards a Framework for Evaluating Explanations in Automated Fact Verification](https://mlsanity.com/paper/2403.20322/) (2024)
- [Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training](https://mlsanity.com/paper/2208.08749/) (2022)
- [Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework](https://mlsanity.com/paper/2406.15085/) (2024)
- [Adversarial Attacks Against Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2509.08463/) (2025)
- [Investigating Zero- and Few-shot Generalization in Fact Verification](https://mlsanity.com/paper/2309.09444/) (2023)
- [Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model Approach](https://mlsanity.com/paper/2402.06443/) (2024)
- [Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish](https://mlsanity.com/paper/2403.00411/) (2024)
- [AMREx: AMR for Explainable Fact Verification](https://mlsanity.com/paper/2411.01343/) (2024)
- [textitLinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models](https://mlsanity.com/paper/2403.16432/) (2024)
- [Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection](https://mlsanity.com/paper/2501.14728/) (2025)
- [LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems](https://mlsanity.com/paper/2601.16890/) (2026)
- [FinGen: A Dataset for Argument Generation in Finance](https://mlsanity.com/paper/2405.20708/) (2024)
- [AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification](https://mlsanity.com/paper/2604.07967/) (2026)

## Abstract (arXiv)

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick a model into predicting a target class. However, for inference tasks such as fact checking, these triggers often inadvertently invert the meaning of instances they are inserted in. In addition, such attacks produce semantically nonsensical inputs, as they simply concatenate triggers to existing samples. Here, we investigate how to generate adversarial attacks against fact checking systems that preserve the ground truth meaning and are semantically valid. We extend the HotFlip attack algorithm used for universal trigger generation by jointly minimising the target class loss of a fact checking model and the entailment class loss of an auxiliary natural language inference model. We then train a conditional language model to generate semantically valid statements, which include the found universal triggers. We find that the generated attacks maintain the directionality and semantic validity of the claim better than previous work.