Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

https://arxiv.org/abs/2607.20723v1

Core Idea

LeakyLMs introduces a set of attacks that leak proprietary model architecture and deployment information from production language models using only per-token generation timing.

For this daily profile, it is worth opening because it links Attention, Inference, and Language to a concrete method, not just a broad trend.

What Is New

The novelty signal is concentrated around Attention, Inference, Language, and Model. For this profile, the important question is whether the paper changes how architecture ideas are generated, evaluated, or connected to software and hardware constraints.

Methodology

Read this as a loop: define the target system, apply the proposed mechanism, measure against a baseline, then use the measured signal to justify the next design choice. Mechanism: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. Evidence: LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs.

score(design) = quality_metric(design) - cost_to_evaluate(design) + feedback_gain(design)

Figure To Read First

Read this visual first: focus on the first architecture, workflow, or pipeline figure before the experiments. It should show what is optimized, what feedback signal is used, and where the system boundary sits.

Minimal Mental Model

research artifact
  question      -> what design, runtime, or system boundary changes?
  mechanism     -> model, agent, compiler, simulator, or hardware feedback
  evaluation    -> baseline comparison plus cost / latency / accuracy signal
  reusable idea -> what should carry into the next architecture experiment?

Why It Matters

Paper recommendations matter when they sharpen the research map: what problem is now easier to study, what methodology becomes reusable, and which architecture assumptions should be questioned next.