Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.08877 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912947077382144 |
|---|---|
| author | Daniels, Oliver Moodley, Perusha Marlin, Benjamin M. Lindner, David |
| author_facet | Daniels, Oliver Moodley, Perusha Marlin, Benjamin M. Lindner, David |
| contents | Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We address this gap, implementing an automatic red-team pipeline that generates deception strategies (in the form of system prompts) tailored to specific white-box and black-box auditing methods. Stress-testing assistant prefills, user persona sampling, sparse autoencoders, and token embedding similarity methods against secret-keeping model organisms, our automatic red-team pipeline finds prompts that deceive both the black-box and white-box methods into confident, incorrect guesses. Our results provide the first documented evidence of activation-based strategic deception, and suggest that current black-box and white-box methods would not be robust to a sufficiently capable misaligned model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08877 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stress-Testing Alignment Audits With Prompt-Level Strategic Deception Daniels, Oliver Moodley, Perusha Marlin, Benjamin M. Lindner, David Machine Learning Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We address this gap, implementing an automatic red-team pipeline that generates deception strategies (in the form of system prompts) tailored to specific white-box and black-box auditing methods. Stress-testing assistant prefills, user persona sampling, sparse autoencoders, and token embedding similarity methods against secret-keeping model organisms, our automatic red-team pipeline finds prompts that deceive both the black-box and white-box methods into confident, incorrect guesses. Our results provide the first documented evidence of activation-based strategic deception, and suggest that current black-box and white-box methods would not be robust to a sufficiently capable misaligned model. |
| title | Stress-Testing Alignment Audits With Prompt-Level Strategic Deception |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.08877 |