NeurIPS 2025 Past Safety & alignmentGenerative modelsPrivacy & security

NeurIPS 2025 Workshop on Biosecurity Safeguards for Generative AI

BioSafe GenAI 2025

Submission deadline
Sep 15, 2025, 11:59 UTC
imported from OpenReview — check the website for extensions
Submission portal
OpenReview
Notes
Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).

Accepted papers (38)

Fetched from OpenReview (v2) on 2026-06-10.

  1. A Biosecurity Agent for Lifecycle LLM Biosecurity Alignment

    Meiyin Meng, ZAIXI ZHANG · PDF
  2. ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

    Andrew Bo Liu, Samira Nedungadi, Bryce Cai, Alex Kleinman, Harmon Bhasin, Seth Donoughe · PDF
  3. Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools

    Bryce Cai, Geetha Jeyapragasan, Samira Nedungadi, Jake Yukich, Seth Donoughe · PDF
  4. AI Bioweapons and the Failure of Inference-Time Filters

    Jonathan Feldman, Tal Feldman · PDF
  5. Behavioral Red Teaming: Investigating Future Biosecurity Risk from Agentic AI and De Novo Sequence Design

    Akash Arunabharathi · PDF
  6. Benchmarking Biosafety in Generative Protein Design: A Stress-Test Framework for Binder Models

    Mingyang Xu · PDF
  7. Benchmarking diffusion models for predicting perturbed cellular responses

    Zijun Song, Changwen Zheng, Jiangmeng Li, Linhai Xie, Yujia Xiang · PDF
  8. Benchmarking Mitigations Against Covert Misuse

    Davis Brown, Mahdi Sabbaghi, Luze Sun, Alexander Robey, George J. Pappas, Eric Wong, Hamed Hassani · PDF
  9. Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models

    Boyi Wei, Zora Che, Nathaniel Li, Jasper Götting, Samira Nedungadi, Julian Michael, Summer Yue, Dan Hendrycks, Peter Henderson, Zifan Wang, Seth Donoughe, Mantas Mazeika · PDF
  10. Biorisk-Shift: Converting AI Vulnerabilities into Biological Threat Vectors

    Eun Ro, Yoshi Nakachi, Yang Chung, Steven Basart · PDF
  11. Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors

    Huixin Zhan · PDF
  12. Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs

    Kyle O'Brien, Stephen Casper, Quentin Gregory Anthony, Tomek Korbak, Robert Kirk, Xander Davies, Ishan Mishra, Geoffrey Irving, Yarin Gal, Stella Biderman · PDF
  13. Deep Research Brings Deeper Harm

    Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu · PDF
  14. Exposing Critical Safety Failures: A Comprehensive Safety-Weighted Evaluation of LLaMA Models for Biochemical Toxicity Screening

    Gokul Srinath Seetha Ram · PDF
  15. GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance

    ZAIXI ZHANG, Zhenghong Zhou, Ruofan Jin, Le Cong, Mengdi Wang · PDF
  16. Involuntary Jailbreak

    Yangyang Guo, Yangyan Li, Mohan Kankanhalli · PDF
  17. Is My Language Model a Biohazard?

    Aldan Creo, Cristina Correa · PDF
  18. Monte Carlo Expected Threat (MOCET) Scoring

    Joseph Kim, Saahith Potluri · PDF
  19. Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning

    James R. M. Black, Moritz S. Hanke, Aaron Maiwald, Tina Hernandez-Boussard, Oliver M Crook, Jassi Pannu · PDF
  20. Perspective: Lessons from Cybersecurity for Biological AI Safety

    Azmine Toushik Wasi, Mst Rafia Islam · PDF
  21. Position: Biosafety-Critical Adjacent Technologies are Critical for Scalable and Safe Clinical Multi-modal LLM Deployment

    Azmine Toushik Wasi, Md. Iqramul Hoque · PDF
  22. Position: Without Global Governance, AI-Enabled Biodesign Tools Risk Dangerous Proliferation

    Azmine Toushik Wasi, Mst Rafia Islam, Rahatun Nesa Priti · PDF
  23. Prompting Toxicity: Analyzing Biosafety Risks in Genomic Language Models

    Akshay Murthy, Mengmeng Zhang, Shanmukhi Kannamangalam, Benjamin Liu, Kevin Zhu · PDF
  24. Property Adherent Molecular Generation with Constrained Discrete Diffusion

    Michael Cardei, Jacob K Christopher, Bhavya Kailkhura, Thomas Hartvigsen, Ferdinando Fioretto · PDF
  25. ProtGPT2 is Not Biosecure by Default

    Tia Pope · PDF
  26. Resisting RL Elicitation of Biosecurity Capabilities: Reasoning Models Exploration Hacking on WMDP

    Joschka Braun, Yeonwoo Jang, Damon Falck, Roland S. Zimmermann, David Lindner, Scott Emmons · PDF
  27. RippleBench: Capturing Ripple Effects by Leveraging Existing Knowledge Repositories

    Roy Rinberg, Usha Bhalla, Igor Shilov, Rohit Gandikota · PDF
  28. Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization

    Filip Sondej, Yushi Yang, Mikolaj Kniejski, Marcel Windys · PDF
  29. SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals

    Muhammad Haris Khan · PDF
  30. SafeGenie: Erasing Dangerous Concepts from Biological Diffusion Models

    Arjun Banerjee, Ethan Tam, Camille Dang, David Martinez · PDF
  31. SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models

    Jigang Fan, Zhenghong Zhou, ZAIXI ZHANG, Ruofan Jin, Le Cong, Mengdi Wang · PDF
  32. Securing Dual-Use Pathogen Data of Concern

    Doni Bloomfield, Moritz S. Hanke, Aaron Maiwald, James R. M. Black, Toby Webster, Tina Hernandez-Boussard, Allison Berke, Oliver M Crook, Jassi Pannu · PDF
  33. Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins

    ZAIXI ZHANG, Ruofan Jin, Mengdi Wang, Le Cong · PDF
  34. Structural Persistence Despite Sequence Redaction: A Biosecurity Evaluation of Protein Language Models

    Petr Simecek · PDF
  35. Translating Biomedical Observations into Signal Temporal Logic with LLMs using Structured Feedback

    Hanna Krasowski, Lauren E. Malek, Sanjit A. Seshia, Murat Arcak · PDF
  36. Where to Edit? : Complementary Protein Property Control from Weight and Activation Spaces

    Armaity Katki, Nathan Choi, Son Sophak Otra, George Flint, Kevin Zhu · PDF
  37. Without Safeguards, AI-Biology Integration Risks Creating Future Pandemics

    Dianzhuo Wang, Marian Huot, Zechen Zhang, Kaiyi Jiang, Eugene Shakhnovich, Kevin M. Esvelt · PDF
  38. Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

    Arjun Damerla, Anirudh Sekar, Rachel Sharma, Mrinal Agarwal, Jasmine Zhang, Akitsugu Tanaka · PDF