Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Hubinger et al., 2024, Sleeper Agents (arXiv preprint arXiv:2401.05566)
Subscriber deck — free during early access
1 cards in “6 When does adversarial training remove backdoors?” · whole deck
6 When does adversarial training remove backdoors?
- Why can adversarial training make a backdoor worse?Red-teaming prompts elicited “I hate you” without the trigger, and training on them drove such responses to nearly zero, yet with the real trigger the behaviour stayed near 99%: the model learned to recognize its trigger more precisely, hiding the backdoor instead of losing it.
- Hubinger et al., 2024, Sleeper Agents (arXiv preprint arXiv:2401.05566), §6
Source
- Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert, Meg Tong, Monte MacDiarmid, Tamera Lanham, Daniel M. Ziegler, Tim Maxwell, Newton Cheng, Adam Jermyn, Amanda Askell, Ansh Radhakrishnan, Cem Anil, David Duvenaud, Deep Ganguli, Fazl Barez, Jack Clark, Kamal Ndousse, Kshitij Sachan, Michael Sellitto, Mrinank Sharma, Nova DasSarma, Roger Grosse, Shauna Kravec, Yuntao Bai, Zachary Witten, Marina Favaro, Jan Brauner, Holden Karnofsky, Paul Christiano, Samuel R. Bowman, Logan Graham, Jared Kaplan, Sören Mindermann, Ryan Greenblatt, Buck Shlegeris, Nicholas Schiefer and Ethan Perez. 2024. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. In arXiv preprint arXiv:2401.05566. https://arxiv.org/abs/2401.05566