Raza et al., Blockchain Security: An Empirical Evaluation of High-Impact Exploits and Detection Tools

Evidence record

Open access, peer-reviewed October 9 study. Section 8.6 compares GPTScan pipeline with direct model analysis on a 106-contract suite.

Read the original source ↗

Claim-level citations (3)

• supportsGPTScan preprocessing filtered most benchmark contracts before model review: Adapted GPTScan yielded zero benchmark-relevant detections across 53 vulnerable contracts, and the authors attribute much of the mismatch to GPTScan’s specialized logic-vulnerability scope.

  Table 7 and Section 8.6.2

• supportsGPTScan preprocessing filtered most benchmark contracts before model review: With the same model directly analyzing all 106 contracts in three medium-effort passes, the study recorded 24 true positives, four false positives and 29 false negatives.

  Table 7 and Section 8.6.3

• supportsGPTScan preprocessing filtered most benchmark contracts before model review: The Falcon prefilter forwarded eight of 106 contracts to GPT-5.6-terra, of which only two were vulnerable under the benchmark labels.

  Section 8.6.2, GPTScan pipeline and Falcon prefilter