Security
Hugging Face Tokenizer Flaw Enables MitM Attacks on Local
HiddenLayer disclosed on May 12, 2026 that Hugging Face's tokenizer layer can be weaponized via a…
Tag: open-source AI
Security
Hugging Face Tokenizer Flaw Lets Attackers Hijack
HiddenLayer researchers disclosed a tokenizer vulnerability in Hugging Face that lets attackers hijack locally-run open-source models…
Security
Hugging Face Models Weaponized via Tokenizer Files
HiddenLayer researchers revealed on May 12, 2026 that a single modified tokenizer JSON file can hijack…
AI
Poolside Launches Free Laguna XS.2 as Open Source AI
Poolside launched free Laguna XS.2 models for coding tasks while Xiaomi released efficient MiMo-V2.5 variants, intensifying…
Security
Open Source AI Models Face New Security and Ethics Challenges
Open source AI models like Llama and Mistral are democratizing AI access while creating new security…