Which vulnerabilities of LLMs are the most imminent & critical to guard against?

Machine Learning (ML)Artificial Intelligence (AI)

Prompt injection15%

Insecure plug-in design48%

Insecure output handling26%

Sensitive information disclosure12%

Model Denial of Service

113 PARTICIPANTS
844 viewscircle icon1 Comment
Sort by:
CISO in Software2 years ago

On this topic, recommend checking out Caleb Sima recent talk: https://www.youtube.com/watch?v=q_gDtOu1_7E&t=1s&ab_channel=CloudSecurityAlliance

Content you might like

Which pitfalls—model bias, false positives/negatives, data quality, regulatory constraints—often impede AI-based security tools, and how can they be mitigated in a financial-services context?

Read More Comments

Do your exposure management processes also address your identity attack surface?

Yes37%

Not yet – we’re working to integrate identity attack surface54%

No7%

Unsure2%

View Results

How many users in your organization have access privileges beyond what they require?

All users11%

Some users48%

A few users33%

No users4%

Unsure1%

View Results

How are you establishing accountability for AI governance, data quality, and responsible AI practices? Is this centralized with specific roles, or distributed across IT teams?

Read More Comments

As a CIO, what do you see as your most critical responsibility when leading AI-driven talent transformation initiatives?

Read More Comments