I explain application security using comic art.
Joined April 2023
- Tweets743
- Following518
- Followers603
- Likes3K
Pinned Tweet
In February, I discovered a critical authentication bypass in the Google Cloud API Gateway and reported it to @GoogleVRP. 🧵[1/10]
References:
Write-Up: securingbits.com/bypassing-g…
CVE: nvd.nist.gov/vuln/detail/CVE…
GitHub Advisory: github.com/GoogleCloudPlatfo…
#bugbounty #googlecloud
Building your next LLM integration?
Beware of Indirect Prompt Injection vulnerability. Previous models like GPT4 and Bing have been affected.
#llm #applicationsecurity #chatgpt
Learn more about indirect prompt injections from the paper 'Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection'
Link: arxiv.org/pdf/2302.12173
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
Building your next LLM integration?
Beware of Indirect Prompt Injection vulnerability. Previous models like GPT4 and Bing have been affected.
#llm #applicationsecurity #chatgpt
HTTP Response Headers: Usage 🛠 and Security Abuse ☠.
Those complement the HTTP Request Headers we saw last week :)
#websecurity #bugbounty #bugbountytips
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
HTTP Response Headers: Usage 🛠 and Security Abuse ☠.
Those complement the HTTP Request Headers we saw last week :)
#websecurity #bugbounty #bugbountytips
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
Guard your LLM against prompt injection with these powerful tools:
- github.com/protectai/llm-gua…
- github.com/protectai/rebuff
- github.com/NVIDIA/NeMo-Guard…
- github.com/amoffat/HeimdaLLM
- github.com/guardrails-ai/gua…
- github.com/whylabs/langkit
#AI #MachineLearning #LLM #Security 🛡️🔒
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
Guard your LLM against prompt injection with these powerful tools:
- github.com/protectai/llm-gua…
- github.com/protectai/rebuff
- github.com/NVIDIA/NeMo-Guard…
- github.com/amoffat/HeimdaLLM
- github.com/guardrails-ai/gua…
- github.com/whylabs/langkit
#AI #MachineLearning #LLM #Security 🛡️🔒
What could go wrong during the ML model development lifecycle (Part 2) ?
Example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by @d1gital_f and James Callaghan of @controlplaneio
at @CloudNativeFdn.
#ai #machinelearning #security
If you missed Part 1 👇
xitter.cf/securing_bits/status/1…
What could go wrong during the ML model development lifecycle?
Example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by @d1gital_f and James Callaghan of @controlplaneio at
@CloudNativeFdn.
Talk: youtube.com/watch?v=gjl-lTF7…
#ai #machinelearning #security
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
What could go wrong during the ML model development lifecycle (Part 2) ?
Example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by @d1gital_f and James Callaghan of @controlplaneio
at @CloudNativeFdn.
#ai #machinelearning #security
Authentication (AuthN) architecture patterns for microservices👇
#microservices #applicationsecurity #systemdesign
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
Authentication (AuthN) architecture patterns for microservices👇
#microservices #applicationsecurity #systemdesign
What could go wrong during the ML model development lifecycle?
Example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by @d1gital_f and James Callaghan of @controlplaneio at
@CloudNativeFdn.
Talk: youtube.com/watch?v=gjl-lTF7…
#ai #machinelearning #security
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
What could go wrong during the ML model development lifecycle?
Example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by @d1gital_f and James Callaghan of @controlplaneio at
@CloudNativeFdn.
Talk: youtube.com/watch?v=gjl-lTF7…
#ai #machinelearning #security
Take a look at these Google Cloud Threat Detection Queries👇
They are inspired by a talk given by @daycyberwox during a past @fwdcloudsec event.
Link: [youtube.com/watch?v=orNBBHKa…]
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can:
Take a look at these Google Cloud Threat Detection Queries👇
They are inspired by a talk given by @daycyberwox during a past @fwdcloudsec event.
Link: [youtube.com/watch?v=orNBBHKa…]
🧵[2/2] Find the full paper
"Poisoned ChatGPT Finds Work for Idle Hands: Exploring Developers' Coding Practices with Insecure Suggestions from Poisoned AI Models" at arxiv.org/pdf/2312.06227.pdf
I hope you've found this thread helpful.
Follow me here @securing_bits or on Linkedin linkedin.com/in/vasilikos-pa… for more, and if you enjoy my content make sure to subscribe to my weekly free newsletter at securingbits.com/newsletter.
Like/Repost the quote below if you can: