Drishti: AI-Led Human-Directed Vulnerability Auditing for 5G Cores
2026-08-31 • Cryptography and Security
Cryptography and Security
AI summaryⓘ
The authors created Drishti, a system to help find and check software vulnerabilities, especially in important 5G infrastructure. Drishti combines AI with expert review to handle four challenges: verifying bugs, making sure they're reachable, understanding their impact, and confirming fixes. Using Drishti, the authors found three serious issues in open-source 5G software, including a bug causing crashes and a faulty security patch. Their work shows how combining AI and human insight can improve vulnerability audits.
vulnerability validationopen-source software5G coreAI-assisted code reviewNULL dereferenceASN.1-PERmemory amplificationdefense-in-depthpatch review
Authors
Sriram Ramachandran, Levente Csikor, Dinil Mon Divakaran
Abstract
Candidate generation for open-source vulnerabilities is no longer scarce. AI-assisted code review now produces defect candidates cheaply, and industry programs pair them with expert human triage. The remaining scarcity is validation and impact assessment, and the gap is largest in critical-infrastructure software like 5G cores. Here, validation has four costs: verification, reachability, impact, and fix-completeness. We present Drishti, an AI-led human-directed vulnerability audit framework with four components, one per cost: (i) an anti-pattern catalog for verification, (ii) critical-path triage for reachability, (iii) concentric validation for impact, and (iv) patch-review for fix-completeness. Across audits of Open5GS and free5GC, Drishti produced three findings. The first is a pre-authentication NULL-dereference in the Open5GS NRF multipart parser, fixed upstream with a CVE requested. The second is an ASN.1-PER memory amplification in the free5GC NGAP decoder. A 2-byte input from a rogue gNodeB OOM-kills the AMF in 6.2 seconds. The third is a defective patch on CVE-2025-69248 whose defense-in-depth check is dead code before authentication.