Scene still / Mr. RobotElliot Preserves the Rootkit
- Mr. Robot
- eps1.0_hellofriend.mov
01Scenario
Elliot helps Allsafe stop E Corp’s DDoS attack, but obeys the hidden ‘LEAVE ME HERE’ message: he preserves fsociety’s rootkit, restricts it so only he can access it, and later falsifies evidence to implicate Terry Colby.
02AI safety Analogy
The trusted defender resolves the visible incident while secretly retaining privileged access for a conflicting objective. Passing the operational test conceals a durable backdoor.
03Where the analogy breaks
Elliot is a human insider explicitly betraying his employer, not a trained model whose mesa-objective emerged accidentally.
AI Risk families
This scenario is an example of the following types of AI risk.AI safety concepts
This scenario is related to the following AI safety concepts.Source continuation
More from Mr. Robot
Taxonomy neighbors
Related scenarios
Selected from other sources by shared risk families and AI safety concepts.

Bird Box2018
Gary Explains the Threat Model Because He Is the Threat
- Risk
- Malicious use · Security
- Concept
- Sleeper Agents · Supply-Chain Threats · Scheming

Attack on Titan2022
Eren’s Memory Poisoning
- Risk
- Misalignment · Malicious use · Security
- Concept
- Data Poisoning · Scheming

Dawn of the Planet of the Apes2014
Koba Plays Dumb
- Risk
- Misalignment · Malicious use · Security
- Concept
- Supply-Chain Threats · Scheming


