# Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions

arXiv: https://arxiv.org/abs/2410.20019 · HTML: https://mlsanity.com/paper/2410.20019/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [TimeLMs: Diachronic Language Models from Twitter](https://mlsanity.com/paper/2202.03829/) (2022)
- [DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models](https://mlsanity.com/paper/2310.00902/) (2023)
- [Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://mlsanity.com/paper/2010.14235/) (2020)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)
- [TweetNLP: Cutting-Edge Natural Language Processing for Social Media](https://mlsanity.com/paper/2206.14774/) (2022)
- [SemAttack: Natural Textual Attacks via Different Semantic Spaces](https://mlsanity.com/paper/2205.01287/) (2022)
- [Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses](https://mlsanity.com/paper/1909.04028/) (2019)
- [Improving the Robustness of Summarization Systems with Dual Augmentation](https://mlsanity.com/paper/2306.01090/) (2023)
- [Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News](https://mlsanity.com/paper/2104.12918/) (2021)
- [Boosting Big Brother: Attacking Search Engines with Encodings](https://mlsanity.com/paper/2304.14031/) (2023)
- [Scalable Fact-checking with Human-in-the-Loop](https://mlsanity.com/paper/2109.10992/) (2021)
- [Harnessing Abstractive Summarization for Fact-Checked Claim Detection](https://mlsanity.com/paper/2209.04612/) (2022)
- [Topic-Guided Abstractive Text Summarization: a Joint Learning Approach](https://mlsanity.com/paper/2010.10323/) (2020)
- [Multi-Document Summarization using Distributed Bag-of-Words Model](https://mlsanity.com/paper/1710.02745/) (2017)
- [Natural Adversarial Sentence Generation with Gradient-based Perturbation](https://mlsanity.com/paper/1909.04495/) (2019)

## Built on by (most cited first, 2 of 2)

- [Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval](https://mlsanity.com/paper/2512.00804/) (2025)
- [Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning](https://mlsanity.com/paper/2606.26036/) (2026)

## Abstract (arXiv)

Large Language Models have introduced novel opportunities for text comprehension and generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks, particularly in tasks like text classification and translation. However, the adversarial robustness of abstractive text summarization models remains less explored. In this work, we unveil a novel approach by exploiting the inherent lead bias in summarization models, to perform adversarial perturbations. Furthermore, we introduce an innovative application of influence functions, to execute data poisoning, which compromises the model's integrity. This approach not only shows a skew in the models behavior to produce desired outcomes but also shows a new behavioral change, where models under attack tend to generate extractive summaries rather than abstractive summaries.