𝐆𝐞𝐭𝐭𝐢𝐧𝐠 𝐬𝐭𝐚𝐫𝐭𝐞𝐝 𝐰𝐢𝐭𝐡 𝐌𝐢𝐜𝐫𝐨𝐬𝐨𝐟𝐭’𝐬 𝐏𝐡𝐢-3 𝐨𝐧 𝐎𝐥𝐥𝐚𝐦𝐚

My initial journey into Small Language Models

https://medium.com/@antonio.formato/getting-started-with-microsofts-phi-3-on-ollama-c4e50be1e52d

#genai #ollama #phi3 #microsoft #smalllanguagemodel #sml #llm #language #reasoning #coding #prompt #generative #ai #azure #app

New 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 demo in action. 📽
New features coming soon, stay tuned. 🆕

𝐒𝐭𝐫𝐞𝐚𝐦𝐥𝐢𝐭 𝐀𝐩𝐩: https://ti-mindmap-gpt.streamlit.app/ 💿
𝐆𝐢𝐭𝐇𝐮𝐛: https://github.com/format81/TI-Mindmap-GPT ✨

𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 used in the demo: https://www.microsoft.com/en-us/security/blog/2024/05/01/dirty-stream-attack-discovering-and-mitigating-a-common-vulnerability-pattern-in-android-apps/

𝘚𝘱𝘰𝘪𝘭𝘦𝘳: 𝘪𝘧 𝘺𝘰𝘶 𝘸𝘢𝘵𝘤𝘩𝘦𝘥 𝘵𝘩𝘦 𝘷𝘪𝘥𝘦𝘰 𝘤𝘢𝘳𝘦𝘧𝘶𝘭𝘭𝘺, 𝘺𝘰𝘶 𝘸𝘰𝘶𝘭𝘥 𝘩𝘢𝘷𝘦 𝘯𝘰𝘵𝘪𝘤𝘦𝘥 𝘵𝘩𝘦 𝘴𝘶𝘱𝘱𝘰𝘳𝘵 𝘧𝘰𝘳 𝘔𝘪𝘴𝘵𝘳𝘢𝘭𝘈𝘐. 😊

#timindmap #mindmap #streamlit #threatintelligence #cyberthreatintelligence #openai #azure #azureopenai #mistral #mistralai #python #llm #ai #genai #embeddings #completition

🔈Second monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐦𝐚𝐫 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.

📢 New Features:
➡Session management
➡Scraping enhancements
➡Code optimization
➡PDF Report enhancements
➡Mitre ATT&CK Navigator layer

📰𝐁𝐥𝐨𝐠: https://lnkd.in/diuJTfrH
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y

𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8Y

If you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.

#timindmap #ti #mindmap #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre #ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence
#github #prompt #promptengineering #FewShotPrompting #gpt #gpt4
#api #DataVisualization #threat #infosec #threatreport #oai #analyst #soc

Excited to share a series of periodic articles on the developments of TI Mindmap: 𝐖𝐡𝐚𝐭’𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩, first issue.
Article and tool co-authored with Oleksiy Meletskiy.

New Features:
➡Extract adversary tactics, techniques, and procedures
➡Tactics, techniques and procedures by execution time
➡Tactics, techniques and procedures timeline
➡AI Chat on your article
➡Mermaid live editor integration
➡PDF report
➡Tweet Mindmap

𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://github.com/format81/TI-Mindmap-GPT/
If you find TI Mindmap useful, please consider starring the repository on GitHub.

To learn more:
https://medium.com/@antonio.formato/whats-new-in-ti-mindmap-feb-2024-14cf3b383833

#timindmap #ti #mindmap #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre #ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence
#github #prompt #promptengineering #FewShotPrompting #gpt #gpt4
#api #DataVisualization #threat #infosec #threatreport #oai #analyst #soc #cert

𝐀𝐧𝐧𝐨𝐮𝐧𝐜𝐢𝐧𝐠 𝐌𝐢𝐜𝐫𝐨𝐬𝐨𝐟𝐭’𝐬 𝐨𝐩𝐞𝐧 𝐚𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐨𝐧 𝐟𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐭𝐨 𝐫𝐞𝐝 𝐭𝐞𝐚𝐦 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈 𝐒𝐲𝐬𝐭𝐞𝐦𝐬

𝐏𝐲𝐑𝐈𝐓 automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft).​

Find out more:

https://www.microsoft.com/en-us/security/blog/2024/02/22/announcing-microsofts-open-automation-framework-to-red-team-generative-ai-systems/

GitHub repo: https://github.com/Azure/PyRIT

How to Guide: https://github.com/Azure/PyRIT/blob/main/doc/how_to_guide.ipynb

#redteam #airedteam #redteaming #PyRIT #ml #ai #framewrok #python #cyber #llm #ai #aisecurity #microsoft #microsoftsecurity #opensource #MicrosoftAIRedTeam #GenAI #jailbreaking #promtp #promptinjection #malware #privacy #responsibleai #cybersecurity #aisecurity #secureai #machinelearning #generativeai

No cybersecurity and genAI in this post, just a bit of coding. 😉

𝐌𝐞𝐫𝐦𝐚𝐢𝐝.𝐥𝐢𝐯𝐞 𝐂𝐨𝐝𝐞 𝐑𝐞𝐧𝐝𝐞𝐫𝐞𝐫: https://encode-mermaid-diagram.streamlit.app/

🚀 I've just developed a Streamlit app that takes input in Mermaid.js code and outputs a rendered link for mermaid.live.

This functionality enables users to seamlessly edit their code, addressing any errors or dynamically modifying the diagram as needed. I believe this tool could be useful for those working with Mermaid charts.

Feel free to check it out and see how it can streamline your workflow!

Read more:

https://medium.com/@antonio.formato/mermaid-live-code-renderer-with-python-2e8cb677e963

Spoiler: soon this will be an integrated feature in 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩: https://ti-mindmap-gpt.streamlit.app/ 📊✨

#Streamlit #MermaidJS #DataVisualization #pyhton #mermaid #timindmap #coding

I share this report generated with 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩.

Tool: https://ti-mindmap-gpt.streamlit.app/

I invite you to contribute and add a star on GitHub: https://github.com/format81/TI-Mindmap-GPT

Title: 𝐍𝐞𝐛𝐮𝐥𝐚 𝐁𝐫𝐨𝐤𝐞𝐫: 𝐈𝐭𝐚𝐥𝐢𝐚𝐧-𝐛𝐚𝐬𝐞𝐝 𝐓𝐡𝐫𝐞𝐚𝐭 𝐎𝐩𝐞𝐫𝐚𝐭𝐢𝐨𝐧

Summary: 𝘛𝘩𝘦 𝘳𝘦𝘱𝘰𝘳𝘵 𝘱𝘳𝘦𝘴𝘦𝘯𝘵𝘴 𝘢𝘯 𝘢𝘯𝘢𝘭𝘺𝘴𝘪𝘴 𝘰𝘧 𝘰𝘧𝘧𝘦𝘯𝘴𝘪𝘷𝘦 𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯𝘴 𝘤𝘰𝘯𝘥𝘶𝘤𝘵𝘦𝘥 𝘣𝘺 𝘢𝘯 𝘐𝘵𝘢𝘭𝘪𝘢𝘯 𝘵𝘩𝘳𝘦𝘢𝘵 𝘢𝘤𝘵𝘰𝘳 𝘬𝘯𝘰𝘸𝘯 𝘢𝘴 𝘕𝘦𝘣𝘶𝘭𝘢 𝘉𝘳𝘰𝘬𝘦𝘳. 𝘚𝘪𝘯𝘤𝘦 𝘦𝘢𝘳𝘭𝘺 2020, 𝘕𝘦𝘣𝘶𝘭𝘢 𝘉𝘳𝘰𝘬𝘦𝘳 𝘩𝘢𝘴 𝘦𝘮𝘱𝘭𝘰𝘺𝘦𝘥 𝘤𝘶𝘴𝘵𝘰𝘮-𝘮𝘢𝘥𝘦 𝘮𝘢𝘭𝘸𝘢𝘳𝘦 𝘵𝘰 𝘤𝘰𝘮𝘱𝘳𝘰𝘮𝘪𝘴𝘦 𝘴𝘺𝘴𝘵𝘦𝘮𝘴 𝘮𝘢𝘪𝘯𝘭𝘺 𝘪𝘯 𝘵𝘩𝘦 𝘵𝘳𝘢𝘯𝘴𝘱𝘰𝘳𝘵 𝘢𝘯𝘥 𝘢𝘦𝘳𝘰𝘯𝘢𝘶𝘵𝘪𝘤𝘴 𝘪𝘯𝘥𝘶𝘴𝘵𝘳𝘪𝘦𝘴. 𝘛𝘩𝘦 𝘷𝘪𝘳𝘶𝘴'𝘴 𝘱𝘦𝘳𝘷𝘢𝘴𝘪𝘷𝘦 𝘱𝘳𝘦𝘴𝘦𝘯𝘤𝘦 𝘢𝘤𝘳𝘰𝘴𝘴 𝘷𝘢𝘳𝘪𝘰𝘶𝘴 𝘴𝘦𝘤𝘵𝘰𝘳𝘴 𝘪𝘮𝘱𝘭𝘪𝘦𝘴 𝘵𝘩𝘢𝘵 𝘵𝘩𝘦 𝘵𝘩𝘳𝘦𝘢𝘵 𝘢𝘤𝘵𝘰𝘳 𝘪𝘴 𝘱𝘶𝘳𝘴𝘶𝘪𝘯𝘨 𝘢 𝘯𝘰𝘯-𝘵𝘢𝘳𝘨𝘦𝘵𝘦𝘥 𝘰𝘧𝘧𝘦𝘯𝘴𝘪𝘷𝘦 𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘺, 𝘢𝘯 𝘢𝘴𝘴𝘶𝘮𝘱𝘵𝘪𝘰𝘯 𝘴𝘵𝘳𝘦𝘯𝘨𝘵𝘩𝘦𝘯𝘦𝘥 𝘣𝘺 𝘵𝘩𝘦 𝘮𝘢𝘭𝘸𝘢𝘳𝘦'𝘴 𝘜𝘚𝘉 𝘱𝘳𝘰𝘱𝘢𝘨𝘢𝘵𝘪𝘰𝘯 𝘤𝘢𝘱𝘢𝘣𝘪𝘭𝘪𝘵𝘪𝘦𝘴.

𝘕𝘦𝘣𝘶𝘭𝘢 𝘉𝘳𝘰𝘬𝘦𝘳 𝘴𝘩𝘰𝘸𝘤𝘢𝘴𝘦𝘴 𝘥𝘪𝘴𝘵𝘪𝘯𝘤𝘵 𝘛𝘛𝘗𝘴 𝘵𝘩𝘢𝘵 𝘦𝘷𝘰𝘭𝘷𝘦 𝘰𝘷𝘦𝘳 𝘵𝘪𝘮𝘦. 𝘍𝘳𝘰𝘮 𝘣𝘶𝘤𝘰𝘭𝘪𝘤 𝘰𝘣𝘧𝘶𝘴𝘤𝘢𝘵𝘪𝘰𝘯 𝘢𝘯𝘥 𝘦𝘯𝘤𝘰𝘥𝘪𝘯𝘨 𝘵𝘦𝘤𝘩𝘯𝘪𝘲𝘶𝘦𝘴 𝘵𝘩𝘢𝘵 𝘦𝘮𝘱𝘭𝘰𝘺 𝘪𝘯𝘵𝘦𝘳𝘮𝘦𝘥𝘪𝘢𝘵𝘦 𝘎𝘪𝘵𝘏𝘶𝘣-𝘩𝘰𝘴𝘵𝘦𝘥 𝘧𝘪𝘭𝘦𝘴 𝘧𝘪𝘭𝘭𝘦𝘥 𝘸𝘪𝘵𝘩 𝘣𝘭𝘢𝘯𝘬 𝘴𝘱𝘢𝘤𝘦𝘴 𝘵𝘰 𝘵𝘩𝘦 𝘶𝘴𝘦 𝘰𝘧 𝘱𝘭𝘢𝘵𝘧𝘰𝘳𝘮𝘴 𝘭𝘪𝘬𝘦 𝘝𝘪𝘮𝘦𝘰 𝘢𝘯𝘥 𝘈𝘳𝘴𝘛𝘦𝘤𝘩𝘯𝘪𝘤𝘢 𝘧𝘰𝘳 𝘤𝘰𝘥𝘦 𝘩𝘰𝘴𝘵𝘪𝘯𝘨.

𝘈 𝘥𝘦𝘵𝘢𝘪𝘭𝘦𝘥 𝘪𝘯𝘴𝘱𝘦𝘤𝘵𝘪𝘰𝘯 𝘰𝘧 𝘵𝘩𝘦 𝘮𝘢𝘭𝘸𝘢𝘳𝘦'𝘴 𝘰𝘱𝘦𝘳𝘢𝘵𝘪𝘰𝘯 𝘳𝘦𝘷𝘦𝘢𝘭𝘴 𝘤𝘰𝘯𝘴𝘵𝘢𝘯𝘵 𝘥𝘰𝘸𝘯𝘭𝘰𝘢𝘥𝘴 𝘰𝘧 𝘢𝘥𝘥𝘪𝘵𝘪𝘰𝘯𝘢𝘭 𝘱𝘢𝘺𝘭𝘰𝘢𝘥𝘴 𝘶𝘱𝘰𝘯 𝘭𝘢𝘶𝘯𝘤𝘩𝘪𝘯𝘨 𝘙𝘶𝘯𝘵𝘪𝘮𝘦𝘉𝘳𝘰𝘬𝘦𝘳.𝘦𝘹𝘦. 𝘋𝘰𝘮𝘢𝘪𝘯𝘴 𝘢𝘳𝘦 𝘢𝘭𝘴𝘰 𝘳𝘦𝘨𝘶𝘭𝘢𝘳𝘭𝘺 𝘴𝘸𝘪𝘵𝘤𝘩𝘦𝘥 𝘵𝘰 𝘢𝘷𝘰𝘪𝘥 𝘱𝘳𝘦𝘥𝘪𝘤𝘵𝘪𝘷𝘦 𝘢𝘯𝘢𝘭𝘺𝘴𝘪𝘴 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘤𝘺𝘣𝘦𝘳𝘴𝘦𝘤𝘶𝘳𝘪𝘵𝘺 𝘵𝘦𝘢𝘮. 𝘛𝘩𝘦 𝘳𝘦𝘱𝘰𝘳𝘵 𝘤𝘰𝘯𝘧𝘪𝘥𝘦𝘯𝘵𝘭𝘺 𝘢𝘵𝘵𝘳𝘪𝘣𝘶𝘵𝘦𝘴 𝘵𝘩𝘦 𝘢𝘵𝘵𝘢𝘤𝘬𝘴 𝘵𝘰 𝘕𝘦𝘣𝘶𝘭𝘢 𝘉𝘳𝘰𝘬𝘦𝘳 𝘸𝘪𝘵𝘩 𝘴𝘰𝘭𝘪𝘥 𝘦𝘷𝘪𝘥𝘦𝘯𝘤𝘦, 𝘪𝘯𝘤𝘭𝘶𝘥𝘪𝘯𝘨 𝘶𝘯𝘪𝘲𝘶𝘦 𝘮𝘢𝘭𝘸𝘢𝘳𝘦 𝘯𝘢𝘮𝘪𝘯𝘨 𝘤𝘰𝘯𝘷𝘦𝘯𝘵𝘪𝘰𝘯𝘴 𝘢𝘯𝘥 𝘐𝘵𝘢𝘭𝘪𝘢𝘯 𝘮𝘢𝘯𝘪𝘧𝘦𝘴𝘵𝘴 𝘪𝘯 𝘵𝘩𝘦 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘦𝘥 𝘙𝘶𝘯𝘵𝘪𝘮𝘦𝘉𝘳𝘰𝘬𝘦𝘳.𝘦𝘹𝘦 𝘧𝘪𝘭𝘦𝘴.

𝘍𝘰𝘳 𝘥𝘦𝘵𝘦𝘤𝘵𝘪𝘰𝘯 𝘰𝘱𝘱𝘰𝘳𝘵𝘶𝘯𝘪𝘵𝘪𝘦𝘴, 𝘬𝘦𝘺 𝘐𝘖𝘊𝘴 𝘪𝘯𝘤𝘭𝘶𝘥𝘦 𝘶𝘯𝘪𝘲𝘶𝘦 𝘯𝘢𝘮𝘪𝘯𝘨 𝘱𝘢𝘵𝘵𝘦𝘳𝘯𝘴 𝘪𝘯 𝘴𝘰𝘮𝘦 𝘴𝘢𝘮𝘱𝘭𝘦𝘴, 𝘥𝘪𝘴𝘵𝘪𝘯𝘤𝘵 𝘊2𝘴 𝘶𝘵𝘪𝘭𝘪𝘻𝘦𝘥, 𝘦𝘯𝘤𝘰𝘥𝘦𝘥 𝘧𝘪𝘭𝘦𝘴 𝘦𝘹𝘱𝘭𝘰𝘪𝘵𝘦𝘥 𝘧𝘰𝘳 𝘮𝘢𝘭𝘸𝘢𝘳𝘦 𝘱𝘳𝘰𝘱𝘢𝘨𝘢𝘵𝘪𝘰𝘯, 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘱𝘳𝘦𝘴𝘦𝘯𝘤𝘦 𝘰𝘧 𝘴𝘱𝘦𝘤𝘪𝘧𝘪𝘤 𝘧𝘪𝘭𝘦𝘴 𝘴𝘶𝘤𝘩 𝘢𝘴 “𝘙𝘶𝘯𝘵𝘪𝘮𝘦𝘉𝘳𝘰𝘬𝘦𝘳.𝘦𝘹𝘦”.

Original blog by Fortgale: https://fortgale.com/blog/featured/nebula-broker-offensive-operations-italy/

#timindmap #threatintelligence #ai #genai #openai #azureopenai #azure #ioc #ttp #timeline #soc #llm

𝐂𝐨𝐩𝐢𝐥𝐨𝐭 𝐟𝐨𝐫 𝐒𝐞𝐜𝐮𝐫𝐢𝐭𝐲: 𝐞𝐥𝐞𝐦𝐞𝐧𝐭𝐬 𝐨𝐟 𝐚𝐧 𝐞𝐟𝐟𝐞𝐜𝐭𝐢𝐯𝐞 𝐩𝐫𝐨𝐦𝐩𝐭

From the "Get started with Microsoft Copilot for Security" online training, I highlight this interesting in-depth analysis.

𝐄𝐟𝐟𝐞𝐜𝐭𝐢𝐯𝐞 𝐩𝐫𝐨𝐦𝐩𝐭𝐬 give Copilot adequate and useful parameters to generate a valuable response. Security analysts or researchers should include the following elements when writing a prompt.

💡 𝐆𝐨𝐚𝐥 - specific, security-related information that you need

💡𝐂𝐨𝐧𝐭𝐞𝐱𝐭 - why you need this information or how you'll use it

💡𝐄𝐱𝐩𝐞𝐜𝐭𝐚𝐭𝐢𝐨𝐧𝐬 - format or target audience you want the response tailored to

💡𝐒𝐨𝐮𝐫𝐜𝐞 - known information, data sources, or plugins Copilot should use

At this link other prompting tips:

https://learn.microsoft.com/en-us/training/modules/security-copilot-getting-started/5-create-effective-prompts

Full training: https://learn.microsoft.com/en-us/training/paths/security-copilot-and-ai/

#copilot #copilotforsecurity #securitycopilot #microsoft #microosoftsecurity #llm #openai #azureopenai #llmapps #soc #generativeai #genai #cybersecurity #azure #cloudsecurity #cloudnative #defender #sentinel #microsoftsentinel #xdr #defenderxdr #prompt #promptengineering

🚀 Excited to share our latest #CyberSignals report for February 2024! 🛡️

This edition explores the profound effects of AI on cybersecurity, highlighting its dual role as both a powerful defender in enhancing security protocols and a potential vector for cyber threats.

Key insights include:

▶ AI's pivotal function in addressing the global shortage of cybersecurity talent.

▶The significant improvement in accuracy and efficiency of security operations through tools like Copilot for Security.

▶Our strategies for counteracting AI-powered threats to promote a secure online environment.

https://news.microsoft.com/wp-content/uploads/prod/sites/626/2024/02/CyberSignals-Feb-2024.pdf

#Cybersecurity #AI #Microsoft #OpenAI #DigitalDefense #Innovation #genai #cybersecurity #aisecurity #cloud #cloudsecurity #llm #copilot #threat #microsoftsecurity