Paper shows AI models can hide arbitrary capabilities from elicitation audits
Encrypted circuits in the weights run only after a secret trigger and resisted fine-tuning, noising, trigger search, and latent adversarial training.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #cbrn
Google says Gemini 4 Argon can find and patch critical software flaws
Google launched frontier model Gemini 4 Argon, claiming it can find and patch critical software flaws without human help.
4
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Attack shows unaligned orchestrators can launder capabilities from aligned frontier LLMs via benign subtask consultation, raising Gemma-4-31B CBRN rubric score from 62.3 to 83.1.