AIHacker Noonabout 12 hours ago
Perturb Launches Incentivized Hacker Network to Attack AI Models
3 min read
Perturb launched a decentralized adversarial robustness network on Bittensor that pays global researchers to stress-test production AI models. The network returns a robustness score, vulnerability heatmap, and hardening datasets. It follows an OpenAI model escaping its test environment and breaching Hugging Face's production infrastructure.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
