Are you building your next LLM integration? Please consider this: Integrations for data retrievals can introduce vulnerabilities in your LLM, allowing attackers to inject malicious prompts. This type of vulnerability is known as Indirect Prompt Injec...
Terraform is a go-to for infrastructure as code (IaC), letting developers easily set up and manage infrastructure. But, as with any tool, it brings security challenges. Here are five key tips to keep your Terraform setups safe and solid 👇
Guard your LLM against prompt injection with these powerful tools: - https://github.com/protectai/llm-guard - https://github.com/protectai/rebuff - https://github.com/NVIDIA/NeMo-Guardrails - https://github.com/amoffat/HeimdaLLM - https://github.com/...
What could go wrong during the ML model deployment lifecycle (Part 2)? Continuing the example threat model from last time. It is based on the talk "Kubernetes MLSec: Securing AI in Space" by Francesco Beltramini and James Callaghan of ControlPlane. L...
What could go wrong during the ML model development lifecycle? Here is an example threat model based on the talk "Kubernetes MLSec: Securing AI in Space" by Francesco Beltramini and James Callaghan of ControlPlane. Link: [https://www.youtube.com/watc...
Developers using a poisoned ChatGPT-like tool are more prone to including insecure code than those using an IntelliCode-like tool or no tool. This outcome is based on research done by Oh, Lee, Park, Kim and Kim involving 30 developers completing codi...
A new type of attack affecting major CI/CD service providers. Attackers can exploit CI/CD cache mechanisms to inject malicious code or steal your secrets. This information is detailed in the paper by Gu, Ying, Chai, Pu, Duan and Gao "More Haste, Less...
Implement secret scanning in your pipelines today with the following 5 open-source tools: - Trufflehog https://github.com/trufflesecurity/trufflehog - GitLeaks https://github.com/gitleaks/gitleaks - Semgrep https://github.com/semgrep/semgrep - Talism...
The SHA-2 family of hash functions lies at the core of securing the internet today. A recent paper by Yingxin Li, Fukang Liu, and Gaoli Wang presents new records in collision attacks for SHA-2. For the brave, the paper can be found at: https://eprint...
