% Key papers for Adversarial prompts for language models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2020_is_103001,
  title = {{Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6311},
}

@inproceedings{iclr2020_freelb_29377,
  title = {{FreeLB: Enhanced Adversarial Training for Natural Language Understanding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=BygzbyHFvB},
}

@inproceedings{neurips2021_adversarial_61771,
  title = {{Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=GF9cSKI3A_q},
}

@inproceedings{iclr2021_infobert_30543,
  title = {{InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3123},
}

@inproceedings{iclr2021_towards_30587,
  title = {{Towards Robustness Against Natural Language Word Substitutions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2924},
}

@inproceedings{icml2019_improving_37444,
  title = {{Improving Neural Language Modeling via Adversarial Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3888},
}

@inproceedings{aaai2021_token_1516,
  title = {{Token-Aware Virtual Adversarial Training in Natural Language Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08410-token-aware-virtual-adversarial-training-in-natural-language-understanding/},
}

@inproceedings{neurips2021_how_63213,
  title = {{How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26092},
}

@inproceedings{neurips2023_are_67956,
  title = {{Are aligned neural networks adversarially aligned?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71817},
}

@inproceedings{iclr2024_training_34295,
  title = {{Training Socially Aligned Language Models on Simulated Social Interactions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18780},
}

@inproceedings{aaai2022_the_2831,
  title = {{The King Is Naked: On the Notion of Robustness for Natural Language Processing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11047-the-king-is-naked-on-the-notion-of-robustness-for-natural-language-processing/},
}

@inproceedings{iclr2024_an_34571,
  title = {{An LLM can Fool Itself: A Prompt-Based Adversarial Attack}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18503},
}

@inproceedings{neurips2024_improving_71499,
  title = {{Improving Alignment and Robustness with Circuit Breakers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95761},
}

@inproceedings{aaai2024_mathattack_6609,
  title = {{MathAttack: Attacking Large Language Models towards Math Solving Ability}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29949},
}

@inproceedings{neurips2024_efficient_70770,
  title = {{Efficient Adversarial Training in LLMs with Continuous Attacks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96357},
}

@inproceedings{aaai2021_bigram_201,
  title = {{Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00706-bigram-and-unigram-based-text-attack-via-adaptive-monotonic-heuristic-search/},
}

@inproceedings{iclr2022_on_31510,
  title = {{On Robust Prefix-Tuning for Text Classification}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/5987},
}

@inproceedings{icml2022_certified_40328,
  title = {{Certified Robustness Against Natural Language Attacks by Causal Intervention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17857},
}

@inproceedings{neurips2022_adversarial_64779,
  title = {{Adversarial training for high-stakes reliability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/52876},
}

@inproceedings{neurips2024_robust_73524,
  title = {{Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93953},
}

@inproceedings{neurips2024_rainbow_71250,
  title = {{Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95993},
}

@inproceedings{icml2025_advprompter_47992,
  title = {{AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44613},
}

@inproceedings{neurips2025_adversarial_78510,
  title = {{Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=fYjF9KIJd5},
}

@inproceedings{iclr2025_robust_83673,
  title = {{Robust LLM safeguarding via refusal feature adversarial training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28144},
}

@inproceedings{aaai2025_against_8069,
  title = {{Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34533},
}

@inproceedings{icml2024_revisiting_43690,
  title = {{Revisiting Character-level Adversarial Attacks for Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34762},
}

@inproceedings{icml2025_autoadvexbench_46676,
  title = {{AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45896},
}

@inproceedings{neurips2025_erasing_76797,
  title = {{Erasing Conceptual Knowledge from Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=N5V3dlIck9},
}

@inproceedings{neurips2025_llm_79858,
  title = {{LLM Unlearning via Neural Activation Redirection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=teB4aqJsNP},
}

@inproceedings{iclr2025_dissecting_82539,
  title = {{Dissecting Adversarial Robustness of Multimodal LM Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29257},
}

@inproceedings{iclr2025_adversarial_83059,
  title = {{Adversarial Search Engine Optimization for Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28746},
}

@inproceedings{aaai2026_disentangling_100542,
  title = {{Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37389},
}

@inproceedings{aaai2026_clucert_108785,
  title = {{CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/41137},
}

@inproceedings{aaai2025_harnessing_9412,
  title = {{Harnessing Robust Statistics for Trustworthy AI}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35113},
}