Paper: Black-Box Inference of LLM Architecture via Restricted API
chaumian · x · 2026-07-05
The paper "Black-Box Inference of LLM Architectural Properties with Restrictive API Access" investigates how to infer the architectural properties of large language models using only restricted API access, highlighting implications for model privacy and security.
Related event: Paper Proposes Black-Box Inference of LLM Architecture via Restrictive APIs(2 posts)→
More from Research
- Hierarchical continuous flow language models make pathwise RL more robust to critic exploitation — vxnuaj · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Microsoft's TeleTune evolves agent skills from offline user telemetry — EliasEskin · 2026-10-27
- FlexGlue: sparse-to-dense matching that beats dense accuracy at a fraction of the cost — zhenjun_zhao · 2026-10-27
- PixGR: pixel-space generative decoding for fast feed-forward 3D Gaussian reconstruction — zhenjun_zhao · 2026-10-27