Investigating detection of election-influencing Sleeper Agents using probes
Kenneth Ong · Team Sleeper Ken
Submitted to AI and Democracy Hackathon: Demonstrating the Risks. Sprint projects are early-stage work by participants, not Apart Research publications.
Creates election-influencing Sleeper Agents which wakes up with backdoor-trigger. And tries to detect it using probes
Reviews
Very cool recontextualization of the sleeper agents problem in the context of elections. I think the threat model could be more explicit about ways in which such models could end up being deployed, how likely it is compared to just deploying a regular biased model, and how the backdoor trigger would work in practice. But the basic threat model seems very sound and plausible to me. Good job!
This is an amazing project! What a great demonstration of the risks of sleeper agents on electoral processes. The figure also makes it clear what this might look like in practice and the demonstration quality is very high. I'd be curious which actors would inject these into the application layer, e.g. would it be a pro-Trump developer at a chatbot company using Mistral or something similar? This work could easily be extended into a paper for political scientists or a blog post on concrete risks from Sleeper Agents and I encourage you to take this on! Great work.
Cite this project
@misc{ong2024investigating,
title = {{Investigating detection of election-influencing Sleeper Agents using probes}},
author = {Kenneth Ong},
year = {2024},
month = may,
note = {Submitted to AI and Democracy Hackathon: Demonstrating the Risks, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/investigating-detection-of-election-influencing-sleeper-agents-using-probes}},
url = {https://apartresearch.com/sprints/projects/investigating-detection-of-election-influencing-sleeper-agents-using-probes}
}More from AI and Democracy Hackathon: Demonstrating the Risks
- View project: THE ROLE OF AI IN COMBATING POLITICAL DEEPFAKES IN AFRICAN DEMOCRACIES
THE ROLE OF AI IN COMBATING POLITICAL DEEPFAKES IN AFRICAN DEMOCRACIES
Team 1
The role of AI in combating political deepfakes in African democracies.
- View project: LEGISLaiTOR: A tool for jailbreaking the legislative process
LEGISLaiTOR: A tool for jailbreaking the legislative process
Team Managed Democracy
In this work, we consider the ramifications on generative artificial intelligence (AI) tools in the legislative process in democratic governments. While other research focuses on the micro-level details associated with …
- View project: Subtle and Simple Ways to Shift Political Bias in LLMs
Subtle and Simple Ways to Shift Political Bias in LLMs
Shifty
An informed user knows that an LLM sometimes has a political bias in their responses, but there’s an additional threat that this bias can drift over time, making it even harder to rely on LLMs for an objective …