PulseAugur
EN
LIVE 16:48:28
Deutsch(DE) RT @0x0SojalSec: Reverse-Engineering von Apples Neural Engine und Training eines neuronalen Netzwerks darauf. Apple hat dies nie erlaubt. Die ANE ist nur für In

Researcher reverse-engineers Apple Neural Engine for custom AI training

By PulseAugur Editorial · [2 sources] ·

A security researcher has reverse-engineered Apple's Neural Engine, a specialized chip designed for AI tasks. This process allowed the researcher to train a neural network directly on the engine, an action that Apple has not officially permitted. The Neural Engine is typically restricted to inference operations, suggesting this work may have pushed its capabilities beyond intended use. AI

IMPACT Unlocks potential for custom AI model deployment on Apple hardware, bypassing official channels.

RANK_REASON Reverse-engineering of proprietary hardware for AI training.

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Researcher reverse-engineers Apple Neural Engine for custom AI training

COVERAGE [2]

  1. Mastodon — fosstodon.org TIER_1 Deutsch(DE) · [email protected] ·

    RT @0x0SojalSec: Reverse-Engineered Apple's Neural Engine and trained a neural network on it. Apple never allowed this. The ANE is only for infe

    RT @0x0SojalSec: Reverse-Engineered von Apples Neural Engine und trainierte ein neuronales Netzwerk darauf. Apple hat dies nie erlaubt. Die ANE ist nur für Inferenz ausgelegt, habe sie trotzdem geknackt. Warum es wichtig ist: - M4 ANE 6,6 TFLOPS/W im Vergleich zu 0,08 bei einer A…

    LINKS github.com/…/ANE
  2. Mastodon — fosstodon.org TIER_1 Deutsch(DE) · [email protected] ·

    RT @0x0SojalSec: Reverse-engineering Apple's Neural Engine and training a neural network on it. Apple has never allowed this. The ANE is only for In

    RT @0x0SojalSec: Reverse-Engineering von Apples Neural Engine und Training eines neuronalen Netzwerks darauf. Apple hat dies nie erlaubt. Die ANE ist nur für Inferenz ausgelegt, habe sie trotzdem geöffnet. Warum es wichtig ist: - M4 ANE 6,6 TFLOPS/W vs 0,08 für eine A100 (80× eff…

    LINKS github.com/…/ANE

RELATED ENTITIES

RELATED TOPICS