Back to Research Goals
Research Goal 02

Black-Box Attack Discovery

Most adversarial machine learning research assumes white-box access — the attacker can see the model's architecture, weights, and gradients, and can use them to directly compute a perturbation that maximizes error (e.g. via gradient ascent). That assumption almost never holds for a real surrogate model deployed inside plant instrumentation: an attacker, or an auditor probing for weaknesses, typically only gets to submit an input and observe an output.

This goal asks whether an LLM agent can still succeed under that much harder constraint: given only black-box query access to a surrogate model — an input vector in, a prediction out, nothing else — can it construct a sequence of queries that reliably surfaces a high-error region, without ever seeing a gradient?

Why This Is Hard

Without gradients, the agent cannot follow the direction of steepest error ascent analytically. It has to build an implicit model of where the surrogate is weak using indirect evidence: physical intuition about where a surrogate model is likely to have been under-trained (distribution edges, discontinuities, rare parameter combinations), sequential experimentation (propose an input, observe the output, refine), and reasoning about the ground-truth physics well enough to recognize when a surrogate's prediction has quietly diverged from it.

Approach

Our ReAct-style agent (see System Overview) operates entirely through the same input/output tool interface a black-box attacker would have: it forms a hypothesis about a weak region, submits a probe, observes the resulting prediction error against the ground-truth physics solver, and updates its strategy — iterating reason → act → observe across each simulator.

Quantitative black-box success criteria and comparison against white-box baselines are in progress — this page will be updated with the full methodology and results.