Will a top 10 AI lab be victim of an attempted data poisoning attack by EOY 2027?
1
Ṁ100Ṁ102027
55%
chance
1H
6H
1D
1W
1M
ALL
Resolves YES if an AI lab which ranks among the top 10 AI labs by some reasonable model quality metric reports an attempted (not necessarily successful) data poisoning attack against their models. Also counts if some sufficiently credible third party (such as an embedded evaluator) gave such a report.
Research on data poisoning gives the impression of it being really easy to do, and it being able to implant an undetectable backdoor into a model through well-hidden phantom signatures in a small amount of data. But if that's true then we'd expect to actually see a data poisoning attack soon.
"Writing for the LLMs" doesn't count and probably wouldn't be reported on anyway.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
People are also trading
Related questions
2 of the top 5 AI's are open source at eoy 2027? (ECI)
22% chance
Will a major AI lab announce that the weights of one of its models were compromised in a cyberattack before 2027?
17% chance
Will we actually see someone bomb an AI datacenter before 2027?
90% chance
Will a major AI lab enter the aerospace industry by EOY 2026?
85% chance
Will there be a terrorist attack against OpenAI before 2027?
5% chance
Will any two top AI labs merge by EOY 2027?
7% chance
Will an AI agent at OpenAI, Anthropic, or GDM hack one of the other two labs to steal its research before July 2027?
29% chance
Will an AI datacenter in the US be sabotaged before 2029?
62% chance
Will one AI lab pull ahead before 2028?
33% chance
Will any data center be attacked to oppose AI development by 2030?
89% chance