Jose Selvi
@JoseSelvi
Also in Mastodon at [email protected]
ID:108522183
http://www.pentester.es 26-01-2010 05:39:23
5,6K Tweets
4,5K Followers
272 Following
Good morrow!
I've founded my own company in #CyberSecurity .
Do reach out if I can be of use to you through the services that I offer.
yetanothercyber.com
Have you ever heard that 1 + 1 does not always equal 2? That's the case with prompt injection. In this post, Jose Selvi describes the non-deterministic nature of prompt injection and how to avoid missdetecting such vulnerability. research.nccgroup.com/2024/04/12/nonā¦
š¤ Web LLM attacks
PortSwigger's Web Security Academy write-up on attacking and defending apps that leverage LLMs
š§Ŗ With links to hands-on labs
#cybersecurity #infosec
portswigger.net/web-security/lā¦
If you are using Burp Suite without hackvertor , you are either a bash master or you are not making this game easy at all for yourself!
š¤ Adversarial Attacks on LLMs
š„ post by Lilian Weng covering:
1ļøā£ Threat model
2ļøā£ Types of attacks: token manipulation, gradient based attacks, jailbreaking, human in the loop red teaming, model red teaming
3ļøā£ Mitigations
Love the paper references!
lilianweng.github.io/posts/2023-10-ā¦
Discover the latest insights from our GitHub Security Lab teamās audit on Home Assistant security! š”ļø
github.blog/2023-11-30-secā¦ #CodeReview