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

Machine Learning (ML)Artificial Intelligence (AI)

Prompt injection16%

Insecure plug-in design47%

Insecure output handling26%

Sensitive information disclosure11%

Model Denial of Service

116 PARTICIPANTS
853 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

How are you building enterprise AI capabilities? What factors are driving your build-versus-buy-versus-partner decisions?

Read More Comments

What team compositions and skill sets do you think are essential for AI-enabled IT organizations? What roles or functions are critical to have as you build AI capabilities?

Read More Comments

How many 3rd-party scripts does your website load into web visitors' browsers before they accept or decline your organization's privacy consent notice?

None13%

1-536%

6-1022%

11-2017%

21-492%

50+1%

I don't know6%

View Results

What are some examples of business value creation through AI/Machine Learning?

Read More Comments

How do you monitor and restrict the types of visitor behavior information and PII 3rd-parties can discern, record, or extract via scripts and applications on your website?

We don't use any 3rd-party scripts17%

We can't monitor or restrict 3rd-party script behavior on our website31%

We trust vendors based on initial reviews20%

We test scripts periodically17%

We use Web Privacy Management, WebAppSec, or PriSec Software9%

We outsource website privacy and app security monitoring services3%

Other (please describe)

View Results