black-box testing

Existing threat detection rules lack formal consistency verification against advanced threat models. Method: This paper proposes a unified modeling and verification framework based on labeled transition systems: for the first time, it jointly maps GTDL-based detection rules and attack trees into the LNT (Language of Nested Transitions) formalism, and leverages the CADP toolset to automate system-level verification and iterative refinement via bisimulation and weak trace inclusion. The approach enables structured trace-semantics–driven parsing of attack trees, ensuring both completeness and precision in detecting threat behaviors. Results: Evaluated on real-world malware cases—including LokiBot and Emotet—the method successfully identified multiple semantic mismatches between detection logic and attack models, demonstrating its effectiveness and scalability. This work establishes the first end-to-end, automated formal verification paradigm for certifying the trustworthiness of detection rules.

Addressing the challenge of modeling and formally verifying security in black-box industrial cyber-physical systems (CPS)—such as those in extended supply chains or classified environments—this paper proposes an end-to-end security analysis framework integrating active automata learning with model checking. Our key contribution is the Context-aware Propositional Mapping (CPM) mechanism, which automatically transforms learned Mealy machines into Kripke-like structures, enabling nondeterministic modeling, semantic enrichment, and scalable instantiation of safety properties. The method requires no internal system knowledge, relying solely on input-output interactions to infer behavioral models and verify security properties of communication protocols. We validate its generality, effectiveness, and toolchain reusability across multiple protocols—including NFC and UDS—demonstrating significant improvements in automation and formal assurance for black-box CPS security testing.

This work investigates how external uncertainties propagate through structured multi-agent workflows to induce information contamination, thereby degrading reasoning trajectories and output correctness. We introduce a taxonomy of three distinct manifestations of information contamination along with their control-flow characteristics, establishing the first classification framework tailored to structured multi-agent workflows and a trajectory-based detection and localization methodology. Through systematic injection of structured perturbations across 32 GAIA tasks and 614 experimental configurations involving three diverse models, we uncover a decoupling between workflow structural divergence and answer correctness, exposing the fundamental limitations of current validation mechanisms. These findings provide empirical grounding for the design of robust, defense-oriented multi-agent workflows.

This study addresses the vulnerability of AI-powered software reverse engineering agents to prompt injection attacks by presenting the first systematic investigation of adversarial prompt injections embedded within executable binaries and their obfuscated variants. The work proposes an integrated defense framework that combines static analysis, specialized detection algorithms, and deobfuscation techniques to effectively identify diverse prompt injection attacks in decompiled output. Experimental results demonstrate that the proposed approach maintains high detection accuracy even against heavily obfuscated code, significantly enhancing the security and robustness of AI-driven reverse engineering systems in real-world operational environments.

Addressing the “oracle absence” and “error attribution difficulty” challenges in network protocol parser verification, this paper proposes an LLM-driven framework for RFC semantic parsing and feedback-based oracle refinement. First, large language models automatically translate unstructured RFC text into formal message specifications. Second, an iterative, quasi-oracle is constructed to support specification-guided fuzz testing and cross-language (C/Python/Go) protocol implementation verification. Finally, vulnerabilities are precisely traced back to their originating RFC clauses. This work is the first to integrate LLM-based semantic understanding with dynamic oracle refinement. Evaluated on nine mainstream protocols, it discovers 69 vulnerabilities—36 of which have been confirmed—surpassing state-of-the-art approaches in both effectiveness and efficiency. It also demonstrates, for the first time, the feasibility of fully automated derivation of test oracles directly from natural-language protocol specifications.

This study addresses the inaccuracies inherent in Software Bill of Materials (SBOMs) when characterizing component identities and actual dependencies, particularly their inability to reliably capture code-level hidden dependencies and consistently identify component variants. These limitations lead to inconsistencies between vulnerability reports and Vulnerability Exploitability eXchange (VEX) statements. Through SBOM-driven software composition analysis, evaluation using multiple vulnerability scanners, and consistency checks of VEX assertions, the work systematically reveals significant discrepancies and shortcomings among current mainstream SBOM generation tools in handling these challenges. The findings underscore the need for enhanced mechanisms for dependency representation and component identification, offering critical directions for improving the reliability of vulnerability management practices.

Verifying the equivalence of implementations of the same large model across different frameworks is highly challenging due to significant discrepancies in operator decomposition, tensor layouts, and fusion strategies. This work proposes Emerge, a framework that unifies two implementations into a single e-graph representation, infers candidate equivalences guided by runtime values, and automatically synthesizes rewrite rules on demand without manual intervention. By integrating symbolic SMT-based verification with constraint-aware randomized testing, Emerge supports scenarios involving opaque operators. Experimental results demonstrate that Emerge successfully verifies equivalence for correct implementation pairs, detects 10 out of 13 known bugs, and uncovers 8 previously unknown issues confirmed by developers. The automatically generated block-level rewrite rules achieve effectiveness comparable to handcrafted ones.

Traditional program equivalence checking offers only binary judgments, failing to characterize the scope and conditions under which patches affect program behavior. This work proposes a quantitative partial equivalence analysis method that integrates symbolic execution with a numerical-domain-optimized range-search heuristic to precisely identify regions in the input space where original and patched programs exhibit consistent or divergent behaviors, and to quantify the degree of their differences. By elevating patch impact analysis from qualitative to quantitative, the approach provides reliable lower-bound estimates for equivalence. Experimental evaluation on 90 CVE patches and the Juliet test suite demonstrates its effectiveness, and within EqBench, it successfully uncovered five C program pairs erroneously labeled as equivalent, accurately pinpointing the conditions causing behavioral divergence.

Industrial critical infrastructure software is often deployed as stripped, unsigned binaries, rendering traditional software composition analysis ineffective and challenging existing methods to jointly capture structural and behavioral semantics. This work proposes a semantics-enhanced neuro-symbolic framework that integrates abstract interpretation with a reflective prompting mechanism to constrain a local large language model and suppress hallucinations. It employs a surjective transformation to compress code property graphs into typed software supply chain knowledge graphs and introduces a domain-adapted Graphormer with embedding-space subgraph matching to enable global risk reasoning and zero-day/APT attack identification in opaque binaries. Evaluated on three progressively challenging benchmarks and a hybrid physical-virtual platform comprising real devices from five industrial control vendors, the approach significantly improves detection rates for high-severity CVEs and semantic fidelity while substantially reducing false positives.

This work proposes SCARA, the first end-to-end autonomous repair agent designed to address the challenge of automatically patching vulnerabilities in opaque industrial software (OIS)—systems that lack source code, symbols, and recompilability. Operating entirely at the binary level, SCARA employs a three-stage mechanism comprising operational state-aware validation (OSVA), repair synthesis under semantic constraints (RSA), and correctness verification (CVA). It integrates protocol-level mitigation, binary hardening, and SSCKG-guided patch generation to ensure both feasibility and semantic correctness of repairs. Evaluated on the OIS-RemedBench benchmark, SCARA achieves 100% repair precision with zero false positives, filters out 20.0% of infeasible cases, and attains an 88.9% final repair success rate after retries.