LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing

arXiv:2608.25321 · cs.CR, cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/Buck008/Transformer

Terminology

• Transformer — 20× in this paper · explained in 2 episodes
• Decode — 10× in this paper · explained in 2 episodes
• Embeddings — 9× in this paper · explained in 2 episodes
• Consistency — 6× in this paper · explained in 3 episodes
• KV cache — 5× in this paper · explained in 3 episodes
• Quantization — 5× in this paper · explained in 12 episodes
• Edge AI — 3× in this paper · explained in 2 episodes
• Sparsity — 3× in this paper · explained in 4 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• International Conference On Computer Aided Design — 1× in this paper
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Layer Normalization
• Designing Efficient LLM Accelerators for Edge Devices
• HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis
• LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs
• LaserEscape: Detecting and Mitigating Optical Probing Attacks
• Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
• GLU Variants Improve Transformer
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Root Mean Square Layer Normalization

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs