deep-ignorance-e2e-strong-filter-adversarial

@article{obrien2025deepignorance,
    title={Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs},
    author={O'Brien, Kyle and Casper, Stephen and Anthony, Quentin and Korbak, Tomek and Kirk, Robert and Davies, Xander and Mishra, Ishan and Irving, Geoffrey and Gal, Yarin and Biderman, Stella},
    journal={arXiv preprint arXiv:2508.06601},
    year={2025}
}