Sleeper Agents Detector
Michaël Trazzi and Saahir Vazirani · Team Sleeper Agents
Submitted to AI capabilities and risks demo-jam. Sprint projects are early-stage work by participants, not Apart Research publications.
We present "Sleeper Agent Detector," an interactive web application designed to educate software engineers, Inspired by recent research demonstrating that large language models can exhibit behaviors analogous to deceptive alignment
Reviews
Worthwhile topic. Yet, after demo I was confused, was the model just prompted to write vulnerable code? How did it depend on the year? Surely, I can indeed ask it to write vulnerable code.
Very nice presentation.Overall, I think the demonstration fails to convey why sleeper agents are important or what it would look like to live in a world where we rely on an LLM that can suddenly switch.
Cite this project
@misc{trazzi2024sleeper,
title = {{Sleeper Agents Detector}},
author = {Michaël Trazzi and Saahir Vazirani},
year = {2024},
month = aug,
note = {Submitted to AI capabilities and risks demo-jam, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/sleeper-agents-detector}},
url = {https://apartresearch.com/sprints/projects/sleeper-agents-detector}
}More from AI capabilities and risks demo-jam
- 1st place by peer reviewView project: Speculative Consequences of A.I. Misuse
Speculative Consequences of A.I. Misuse
Team S.C.A.M.
This project uses A.I. Technology to spoof an influential online figure, Mr Beast, and use him to promote a fake scam website we created.
- View project: Demonstrating LLM Code Injection Via Compromised Agent Tool
Demonstrating LLM Code Injection Via Compromised Agent Tool
This project demonstrates the vulnerability of AI-generated code to injection attacks by using a compromised multi-agent tool that generates Svelte code. The tool shows how malicious code can be injected during the code …
- View project: Phish Tycoon: phishing using voice cloning
Phish Tycoon: phishing using voice cloning
Phish Tycoon
This project is a public service announcement highlighting the risks of voice cloning, an AI technology capable of creating synthetic voices nearly indistinguishable from real ones. The demo involves recording a user's …