VendorsBackslash Security
Backslash Security
Cybersecurity reports and statistics published by Backslash Security
6 categories1 reports
Research Reports
Reports and publications from Backslash Security
Recent Statistics & Reports
Prompts specifying a need for security or requesting OWASP best practices produced more secure results, yet still yielded some code vulnerabilities for 5 out of the 7 LLMs tested.
4/24/2025•
AILLMsVulnerabilities
When prompted to generate secure code, GPT-4o still produced insecure outputs vulnerable to 8 out of 10 issues.
4/24/2025•
AILLMsVulnerabilities
In response to simple, “naive” prompts, all LLMs tested generated insecure code vulnerable to at least 4 of the 10 common CWEs.
4/24/2025•
AILLMsVulnerabilities
With naive prompts, ChatGPT scored a 1.5/10 secure code result.
4/24/2025•
AILLMsVulnerabilities
Claude 3.7 Sonnet scored 6/10 secure code result using naive prompts.
4/24/2025•
AILLMsVulnerabilities
OpenAI’s GPT-4o had the lowest performance, scoring a 1/10 secure code result using "naive" prompts.
4/24/2025•
AILLMsVulnerabilities
Claude 3.7 Sonnet scored 10/10 with security-focused prompts.
4/24/2025•
AILLMsVulnerabilities