mlsanityData to 14 Oct 2026

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

arXiv 2505.10983 ↗First posted 16 May 2025cs.LG cs.AI cs.CRcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologically, we evaluate the adversarial robustness of five state-of-the-art GFMs using four widely adopted attack algorithms and three defense strategies. Importantly, our benchmark provides an accessible and comprehensive framework to analyze GFM vulnerabilities with respect to model architecture, quantization schemes, and training datasets. Additionally, we introduce GenoAdv, a new adversarial sample dataset designed to improve GFM safety. Empirically, classification models exhibit greater robustness to adversarial perturbations compared to generative models, highlighting the impact of task type on model vulnerability. Moreover, adversarial attacks frequently target biologically significant genomic regions, suggesting that these models effectively capture meaningful sequence features.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 92 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

53 of 92 references.

References · 53

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  9. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  10. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  11. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  12. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
38 more
  1. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
  2. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 345
  3. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 264
  4. 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 263
  5. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 254
  6. 2017Detecting Adversarial Samples from Artifactscited by 245
  7. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 211
  8. 2023HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolutioncited by 194
  9. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  10. 2019Certified Robustness to Adversarial Word Substitutionscited by 168
  11. 2020Better Fine-Tuning by Reducing Representational Collapsecited by 157
  12. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  13. 2017Generative Adversarial Perturbationscited by 153
  14. 2019Robust Neural Machine Translation with Doubly Adversarial Inputscited by 106
  15. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  16. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 73
  17. 2019Detecting Adversarial Samples Using Influence Functions and Nearest Neighborscited by 72
  18. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 70
  19. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  20. 2018Geometry Score: A Method For Comparing Generative Adversarial Networkscited by 57
  21. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  22. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 56
  23. 2021Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitutioncited by 56
  24. 2018Adversarial Sample Detection for Deep Neural Network through Model Mutation Testingcited by 48
  25. 2018Maximal Jacobian-based Saliency Map Attackcited by 46
  26. 2024Outlier-Efficient Hopfield Layers for Large Transformer-Based Modelscited by 38
  27. 2021Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrificecited by 30
  28. 2023BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attackscited by 21
  29. 2022Text Adversarial Purification as Defense against Adversarial Attackscited by 16
  30. 2025Detection of AI Deepfake and Fraud in Online Payments Using GAN-Based Modelscited by 14
  31. 2024Decoupled Alignment for Robust Plug-and-Play Adaptationcited by 9
  32. 2025Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustnesscited by 9
  33. 2024The Reality of AI and Bioriskcited by 8
  34. 2025Fast and Low-Cost Genomic Foundation Models via Outlier Removalcited by 8
  35. 2022Improving Interpretability via Regularization of Neural Activation Sensitivitycited by 5
  36. 2022In and Out-of-Domain Text Adversarial Robustness via Label Smoothingcited by 5
  37. 2021Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systemscited by 4
  38. 2022FG-UAP: Feature-Gathering Universal Adversarial Perturbationcited by 4

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representationscited by 2
  2. 2026Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors
  2. 2025Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models
  3. 2025AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research
  4. 2026Quantifying Memorization and Privacy Risks in Genomic Language Models
  5. 2026Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
  6. 2024SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
  7. 2025Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models
  8. 2026Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation