Unverified50% confidenceBenchmarkExact time
Veracode's test had more than 100 AI models write code and found that 45% of the code contained known security vulnerabilities.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
Sources
Related Entities
Related Claims
UnverifiedFaced with hundreds or thousands of lines of AI-generated code, using black-box test design techniques can quickly pinpoint high-risk input areas, achieving the highest defect detection rate with limited testing resources.72% similarUnverifiedAn empirical study conducted hardware-level energy measurements on all 1000 EffiBench problems across 11 open-source models and 4 decoding configurations, finding that 42 of the 44 configurations generated code that was more energy-consuming than the human reference implementation.69% similarUnverifiedA security testing project covers more than 2,500 wordlists and payloads, targeting penetration testing, bug bounty hunting, red team operations, and AI security testing.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1176225API
curl https://kongchang.com/api/v1/knowledge/claims/1176225MCP
get_claim(id=1176225)