NLP Security and Ethics, in the Wild
Not on the map. Why?
Abstract (arXiv)
As NLP models are used by a growing number of end-users, an area of increasing importance is NLP Security (NLPSec): assessing the vulnerability of models to malicious attacks and developing comprehensive countermeasures against them. While work at the intersection of NLP and cybersecurity has the potential to create safer NLP for all, accidental oversights can result in tangible harm (e.g., breaches of privacy or proliferation of malicious models). In this emerging field, however, the research ethics of NLP have not yet faced many of the long-standing conundrums pertinent to cybersecurity, until now. We thus examine contemporary works across NLPSec, and explore their engagement with cybersecurity's ethical norms. We identify trends across the literature, ultimately finding alarming gaps on topics like harm minimization and responsible disclosure. To alleviate these concerns, we provide concrete recommendations to help NLP researchers navigate this space more ethically, bridging the gap between traditional cybersecurity and NLP ethics, which we frame as ``white hat NLP''. The goal of this work is to help cultivate an intentional culture of ethical research for those working in NLP Security.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 80 of its 176 references that are in the map. First posted on arXiv 9 Apr 2025.
Builds on
80 of 176 references.
References · 80
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
- 2021Ethical and social risks of harm from Language Modelscited by 966
- 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
- 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
38 more
- 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
- 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
- 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
- 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 263
- 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 222
- 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
- 2021Alignment of Language Agentscited by 168
- 2024Stealing Part of a Production Language Modelcited by 159
- 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
- 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 158
- 2020Contextualized Perturbation for Textual Adversarial Attackcited by 136
- 2023The Semantic Scholar Open Data Platformcited by 118
- 2021Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoningcited by 113
- 2021RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Modelscited by 104
- 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 94
- 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 89
- 2020OpenAttack: An Open-source Textual Adversarial Attack Toolkitcited by 84
- 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
- 2024BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Modelscited by 58
- 2022Fine-mixing: Mitigating Backdoors in Fine-tuned Language Modelscited by 57
- 2022Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Modelscited by 57
- 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
- 2021Beyond Fair Pay: Ethical Implications of NLP Crowdsourcingcited by 53
- 2022BITE: Textual Backdoor Attacks with Iterative Trigger Injectioncited by 53
- 2020Universal Adversarial Attacks with Natural Triggers for Text Classificationcited by 51
- 2022A Study of the Attention Abnormality in Trojaned BERTscited by 48
- 2023NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Modelscited by 37
- 2020TextHide: Tackling Data Privacy in Language Understanding Taskscited by 33
- 2023ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Triggercited by 31
- 2021Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrificecited by 30
- 2021Grey-box Adversarial Attack And Defence For Sentiment Classificationcited by 28
- 2022What a Creole Wants, What a Creole Needscited by 27
- 2023Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakerscited by 27
- 2024Text Embedding Inversion Security for Multilingual Language Modelscited by 26
- 2023Defending against Insertion-based Textual Backdoor Attacks via Attributioncited by 25
- 2024Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queriescited by 25
- 2022Phrase-level Textual Adversarial Attack with Label Preservationcited by 23
- 2021Multi-granularity Textual Adversarial Attack with Behavior Cloningcited by 21
50 most cited of 80 All 80 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.