mlsanityData to 7 Oct 2026

OrderBkd: Textual backdoor attack through repositioning

arXiv 2402.07689 ↗First posted 12 Feb 2024cs.CL cs.AIcited by 2

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

The use of third-party datasets and pre-trained machine learning models poses a threat to NLP systems due to possibility of hidden backdoor attacks. Existing attacks involve poisoning the data samples such as insertion of tokens or sentence paraphrasing, which either alter the semantics of the original texts or can be detected. Our main difference from the previous work is that we use the reposition of a two words in a sentence as a trigger. By designing and applying specific part-of-speech (POS) based rules for selecting these tokens, we maintain high attack success rate on SST-2 and AG classification datasets while outperforming existing attacks in terms of perplexity and semantic similarity to the clean samples. In addition, we show the robustness of our attack to the ONION defense method. All the code and data for the paper can be obtained at https://github.com/alekseevskaia/OrderBkd.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 19 of its 27 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

19 of 27 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks17 Jun
  2. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer14 Oct
  3. 2021BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models6 Oct
  4. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger26 May

Other references · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2020Extracting Training Data from Large Language Modelscited by 2,144
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  9. 2019Learning Deep Transformer Models for Machine Translationcited by 309
  10. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  11. 2018A Survey on Deep Learning for Named Entity Recognitioncited by 281
  12. 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 231
3 more
  1. 2019A backdoor attack against LSTM-based text classification systemscited by 214
  2. 2020BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvementscited by 191
  3. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 44
  2. 2024Invisible Textual Backdoor Attacks based on Dual-Triggercited by 0