OWASP top 10 for LLMs - which ones are you most concerned about for the immediate future?

Threat & Vulnerability ManagementSecurity Frameworks (NIST, CIS, CSF)

Prompt injection13%

Insecure output handling40%

Training data poisoning21%

Model denial of service15%

Supply chain vulnerabilities19%

Sensitive information disclosure29%

Insecure plugin design19%

Excessive agency9%

Over reliance on LLM9%

Model theft4%

169 PARTICIPANTS
1.4k views

Content you might like

Which AI security framework is your primary reference point for governing agentic or LLM-based systems in the next 12 months?

NIST AI Risk Management Framework50%

Google SAIF | Secure AI Foundations10%

CSA MAESTRO20%

OWASP AI Security Guide10%

MITRE ATLAS10%

SAIL Framework

Internally developed

None

View Results

Has anyone used CMMI Cybermaturity framework to benchmark or improve Cybersecurity maturity? I believe it is suitable to large organizations and not small or medium ones. It also needs a lot of time in order to show improvements, do you agree?

Read More Comments

How is AI implementation impacting your organization’s cyber insurance premium or coverage so far?

Has anyone reviewed both the MIT success rate and the ChatGPT success rate?

Read More Comments

How successful have your AI agents been at meeting the goals your organization has set for them?

Highly successful 16%

Moderately successful 42%

Minimally successful 20%

Not successful9%

N/A — we haven’t deployed AI agents13%

Other (comment below)

View Results