AI & ML interests

Open source AI cyber/infosec knowledge and research

Recent Activity

tegridydevΒ  updated a Space about 23 hours ago
openmalx/README
tegridydevΒ  published a Space about 23 hours ago
openmalx/README
View all activity

tegridydevΒ 
posted an update about 23 hours ago
view post
Post
435
Introducing OpenMALx
openmalx


Repository for Infosec and Machine Learning Resources

OpenMALx is an organization focused on the development of datasets and models for security analysis. The project objective is to provide structured data for training and evaluating large language models in a security context.

---

Technical Focus

**Dataset Formatting:** Processing raw security tool logs into instruction/response pairs for model training.
**Local Execution:** Optimizing models for local hardware to ensure data remains on-premises.
**Response Logic:** Developing structured formats for explaining security vulnerabilities and remediation steps.

Active Projects

**infosec-tool-output:** A dataset mapping static and dynamic analysis tool outputs to technical summaries.
openmalx/infosec-tool-output

**open-malsec:** A collection of text-based security threats, including phishing and social engineering samples, for classification tasks.
openmalx/open-malsec
tegridydevΒ 
updated a Space about 23 hours ago
tegridydevΒ 
published a Space about 23 hours ago
tegridydevΒ 
posted an update 11 months ago
view post
Post
2391
Open Source AI Agents | Github/Repo List | [2025]

https://huggingface.co/blog/tegridydev/open-source-ai-agents-directory

Check out the article & Follow, bookmark, save the tab as I will be updating it <3
(using it as my own notepad & decided i might keep it up to date if i post it here, instead of making the 15th_version of it and not saving it with a name i can remember on my desktop lol)
tegridydevΒ 
posted an update 12 months ago
view post
Post
1932
WTF is Fine-Tuning? (intro4devs)

Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? πŸ˜ƒ

Here's a cheat sheet for devs (but open to anyone!)

---

TL;DR

- Full Fine-Tuning: Max performance, high resource needs, best reliability.
- PEFT: Efficient, cost-effective, mainstream, enhanced by AutoML.
- Instruction Fine-Tuning: Ideal for command-following AI, often combined with RLHF and CoT.
- RAFT: Best for fact-grounded models with dynamic retrieval.
- RLHF: Produces ethical, high-quality conversational AI, but expensive.

Choose wisely and match your approach to your task, budget, and deployment constraints.

I just posted the full extended article here
if you want to continue reading >>>

https://huggingface.co/blog/tegridydev/fine-tuning-dev-intro-2025
tegridydevΒ 
posted an update 12 months ago
view post
Post
1476
Open-MalSec v0.1 – Open-Source Cybersecurity Dataset

Evening! 🫑

πŸ“‚ Just uploaded an early-stage open-source cybersecurity dataset focused on phishing, scams, and malware-related text samples.

This is the base version (v0.1)β€”a few structured sample files. Full dataset builds will come over the next few weeks.

πŸ”— Dataset link:

tegridydev/open-malsec

πŸ” What’s in v0.1?
A few structured scam examples (text-based)
Covers DeFi, crypto, phishing, and social engineering
Initial labelling format for scam classification

⚠️ This is not a full dataset yet (samples are currently available). Just establishing the structure + getting feedback.

πŸ“‚ Current Schema & Labelling Approach
"instruction" β†’ Task prompt (e.g., "Evaluate this message for scams")
"input" β†’ Source & message details (e.g., Telegram post, Tweet)
"output" β†’ Scam classification & risk indicators

πŸ—‚οΈ Current v0.1 Sample Categories
Crypto Scams β†’ Meme token pump & dumps, fake DeFi projects
Phishing β†’ Suspicious finance/social media messages
Social Engineering β†’ Manipulative messages exploiting trust

πŸ”œ Next Steps
- Expanding datasets with more phishing & malware examples
- Refining schema & annotation quality
- Open to feedback, contributions, and suggestions

If this is something you might find useful, bookmark/follow/like the dataset repo <3

πŸ’¬ Thoughts, feedback, and ideas are always welcome! Drop a comment or DMs are open πŸ€™
tegridydevΒ 
posted an update 12 months ago
view post
Post
1429
So, what is #MechanisticInterpretability πŸ€”

Mechanistic Interpretability (MI) is the discipline of opening the black box of large language models (and other neural networks) to understand the underlying circuits, features and/or mechanisms that give rise to specific behaviours

Instead of treating a model as a monolithic function, we can:

1. Trace how input tokens propagate through attention heads & MLP layers
2. Identify localized β€œcircuit motifs”
3. Develop methods to systematically break down or β€œedit” these circuits to confirm we understand the causal structure.

Mechanistic Interpretability aims to yield human-understandable explanations of how advanced models represent and manipulate concepts which hopefully leads to

1. Trust & Reliability
2. Safety & Alignment
3. Better Debugging / Development Insights

https://bsky.app/profile/mechanistics.bsky.social/post/3lgvvv72uls2x
  • 1 reply
Β·