FalsifAI: Falsification of AI-Enabled Hybrid Control Systems Guided by Time-Aware Coverage Criteria
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Modern Cyber-Physical Systems (CPSs) that need to perform complex control tasks (e.g., autonomous driving) are increasingly using AI-enabled controllers, mainly based on deep neural networks (DNNs). The quality assurance of such types of systems is of vital importance. However, their verification can be extremely challenging, due to their complexity and uninterpretable decision logic. Falsification is an established approach for CPS quality assurance, which, instead of attempting to prove the system correctness, aims at finding a time-variant input signal violating a formal specification describing the desired behavior; it often employs a search-based testing approach that tries to minimize the robustness of the specification, given by its quantitative semantics. However, guidance provided by robustness is mostly black-box and only related to the system output, but does not allow to understand whether the temporal internal behavior of the neural network controller has been explored sufficiently. To bridge this gap, in this paper, we make an early attempt at exploring the temporal behavior of neural network controllers executed consecutively in hybrid control systems and first propose eight time-aware coverage criteria specifically designed for neural network controllers in the context of CPS, which consider different features by design: the simple temporal activation of a neuron, the continuous activation of a neuron for a given duration, and the differential neuron activation behavior over time. Secondly, we introduce a falsification framework, named FalsifAI, that exploits the coverage information for better falsification guidance. Namely, inputs of the controller that increase the coverage (so improving the exploration of the DNN behaviors), are prioritized in the exploitation phase of robustness minimization. Our large-scale evaluation over a total of 3 typical CPS tasks, 6 system specifications, 18 DNN models, and more than 12000 experiment runs, demonstrates 1) the advantage of our proposed technique in outperforming a state-of-the-art falsification approach, and 2) the usefulness of our proposed time-aware coverage criteria for effective falsification guidance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it