{"ID":2864283,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23806","arxiv_id":"2509.23806","title":"Influence-Guided Concolic Testing of Transformer Robustness","abstract":"Concolic testing for deep neural networks alternates concrete execution with constraint solving to search for inputs that flip decisions. We present an {influence-guided} concolic tester for Transformer classifiers that ranks path predicates by SHAP-based estimates of their impact on the model output. To enable SMT solving on modern architectures, we prototype a solver-compatible, pure-Python semantics for multi-head self-attention and introduce practical scheduling heuristics that temper constraint growth on deeper models. In a white-box study on compact Transformers under small $L_0$ budgets, influence guidance finds label-flip inputs more efficiently than a FIFO baseline and maintains steady progress on deeper networks. Aggregating successful attack instances with a SHAP-based critical decision path analysis reveals recurring, compact decision logic shared across attacks. These observations suggest that (i) influence signals provide a useful search bias for symbolic exploration, and (ii) solver-friendly attention semantics paired with lightweight scheduling make concolic testing feasible for contemporary Transformer models, offering potential utility for debugging and model auditing.","short_abstract":"Concolic testing for deep neural networks alternates concrete execution with constraint solving to search for inputs that flip decisions. We present an {influence-guided} concolic tester for Transformer classifiers that ranks path predicates by SHAP-based estimates of their impact on the model output. To enable SMT sol...","url_abs":"https://arxiv.org/abs/2509.23806","url_pdf":"https://arxiv.org/pdf/2509.23806v1","authors":"[\"Chih-Duo Hong\",\"Yu Wang\",\"Yao-Chen Chang\",\"Fang Yu\"]","published":"2025-09-28T11:09:15Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.LG\"]","methods":"[\"Transformer\",\"LoRA\"]","has_code":false}