Thomas Roccia :verified:

Mastodon @fr0gger@infosec.exchange

⚔ Compare ☆ Watch Own this channel?

🔄 Data last refreshed 4 days ago

🤝

Make a deal with Thomas Roccia :verified:

🔒 Paid proposals held safely in escrow — released only when the work's approved.

Followers

1.6K

Account age

3 yrs

🧰 Free analysis for Thomas Roccia :verified:

🕵️ Fake follower check 📊 Engagement rate 💰 What they charge

Known for

🤓 After 15 years of threat research, I am building something new!
Today, SecurityBreak officially becomes a company focused on AI Threat Intelligence and AI Security!
The new website is live! Check it out :)
https://securitybreak.io

6 views 🤓 After 15 years of threat research, I am building something new! Today, SecurityBreak officially becomes a company focused on AI Threat Intelligence and AI Security! The new website is live! Check it out :) https://securitybreak.io

🤓 GoogleDeepMind released an AI Control Roadmap!
They created TRAIT&R (Taxonomy of Rogue AI Tactics and Routines) which is a MITRE ATT&CK matrix but for AI agents.

6 views 🤓 GoogleDeepMind released an AI Control Roadmap! They created TRAIT&R (Taxonomy of Rogue AI Tactics and Routines) which is a MITRE ATT&CK matrix but for AI agents.

🧐 The Payload is in the Header!!
AI agents are browsing the internet autonomously, which means that if a webpage contains adversarial content, an AI agent can be instructed, manipulated or tricked to conduct malicious actions or get compromised!
But webpage content is not the only attack vector. At

5 views 🧐 The Payload is in the Header!! AI agents are browsing the internet autonomously, which means that if a webpage contains adversarial content, an AI agent can be instructed, manipulated or tricked to conduct malicious actions or get compromised! But webpage content is not the only attack vector. At

🤓 ARD or Agentic Resource Discovery has just been released, so let me explain what it is 👇
When you create an agent, it needs tools, MCP servers, skills and more to interact with the outside world. In practice, you usually have to configure these manually and search for the ones you want.
ARD solves

5 views 🤓 ARD or Agentic Resource Discovery has just been released, so let me explain what it is 👇 When you create an agent, it needs tools, MCP servers, skills and more to interact with the outside world. In practice, you usually have to configure these manually and search for the ones you want. ARD solves

📊 Post engagement

Avg engagement / post

0.2%

Engagement vs followers

Nov 2022

On Mastodon since

🔥 Top post: 🤓 After 15 years of threat research, I am building something new · 6 likes + reposts

📊 Activity & format

Posting cadence

1.3 / week

A lower-frequency account — each post lands with more weight.

Content mix

Mostly images

Recent: 0 text · 10 image · 2 video.

Follower / following

11×

Follows 145 back. A strong ratio — an audience that follows them, not a follow-for-follow network.

Recent posts

View on Mastodon ↗

▶ 🔥 Top post 🤓 After 15 years of threat research, I am building something new! Today, SecurityBreak officially becomes a company focused on AI Threat Intelligence and AI Security! The new website is live! Check it out :) https://securitybreak.io ★ 6

🧐 The Payload is in the Header!! AI agents are browsing the internet autonomously, which means that if a webpage contains adversarial content, an AI agent can be instructed, manipulated or tricked to conduct malicious actions or get compr… ★ 5

I recently updated the web page for my book, you can now find Visual Threat Intelligence here 👇 https://book.securitybreak.io/ ★ 3

▶ "Fable 5 is the most advanced model." Starting a Fable session on my own threat intelligence work 👇🙄 ★ 1

FuzzingLabs has created a curated repo of offensive MCP servers you can wire to your agents! 👇 https://github.com/FuzzingLabs/mcp-security-hub ★ 3

🤓 GoogleDeepMind released an AI Control Roadmap! They created TRAIT&R (Taxonomy of Rogue AI Tactics and Routines) which is a MITRE ATT&CK matrix but for AI agents. ★ 6

🤓 I was recently quoted in the latest @feedly blog by @euphoricall on ASN hunting! Check it out, it is a great piece that covers some techniques that are often overlooked by threat intelligence analysts! 👇 https://feedly.com/ti-essentials/… ★ 1

🤓 ARD or Agentic Resource Discovery has just been released, so let me explain what it is 👇 When you create an agent, it needs tools, MCP servers, skills and more to interact with the outside world. In practice, you usually have to configur… ★ 5

🤓 Attackers are experimenting with different adversarial prompts to bypass your AI analysis pipeline! 👇 Deception Prompt: They trigger safety guardrails with content such as instructions for constructing biological weapon, which makes your… ★ 2

🤓 Unit42 uncovered a prompt injection embedded in a malicious website distributing malicious Excel templates and Chrome extension. The prompt is used to poison SEO and influence AI systems to recommend the website to users, and encourage t… ★ 1

🤓 PromptIntel the database of Adversarial Prompts or Indicator of Prompt Compromise, gets a redesign! Check this out 👇 https://promptintel.novahunting.ai/ ★ 1

🤓 How many times have you questioned claims made in a threat report? The "Trust me bro" is not always reliable! The Admiralty Code also known as the NATO System, is a method used to evaluate collected intelligence. The goal is to assess t… ★ 4

🐘 Community & instance

Home server

infosec.exchange

A cybersecurity & infosec server — its members and audience skew toward that niche, so expect a community-aligned, engaged following.

On Mastodon since

Nov 2022

Joined in the Twitter-exodus wave of late 2022 — part of the migration that made Mastodon a real destination.

💡 Facts

🗓️Joined Mastodon in 2022 — 3 years ago.

👁️Averages 3 views per post.

📤Posts about 1.3× per week.

🛡️ Audience credibility

43/100

Fair Credibility score

73%

Mixed Real audience

Medium Fake-follower risk

High Data confidence

Est. 73% real, active audience · Medium fake-follower risk.
Low engagement (~0.2% of followers engage each post) — a sign of an inflated or inactive audience.
Established account (3+ years old).

Heuristic estimate from engagement, follower ratios, account age & growth — a screening signal, not a guarantee.

About

AI x Threat Intelligence

📸 Gallery

🔀 Audience overlap

Estimated

Estimated shared audience with similar creators — useful for avoiding overlap (or doubling down) when planning a campaign.

dimsumthinking 18%

Donna Yates 16%

Norbert Holstein 12%

impfmilf 11%

Entomological Soc. of America 10%

Global Sumud Flotilla 10%

More like this

Find more →

Mastodon

Donna Yates ✓

@drdonnayates@archaeo.social

1.6K Followers

Mastodon

Norbert Holstein

@dr_norb@fediscience.org

Entomological Soc. of America ✓

@entsocamerica@ecoevo.social

1.6K Followers

Mastodon

Global Sumud Flotilla

@globalsumudflotilla@mastodon.bida.im

1.6K Followers

Mastodon

dimsumthinking

@dimsumthinking@mastodon.social

1.6K Followers

Thomas Roccia :verified:

Make a deal with Thomas Roccia :verified:

Known for

📊 Post engagement

📊 Activity & format

Recent posts

🐘 Community & instance

💡 Facts

🛡️ Audience credibility

About

📸 Gallery

🔀 Audience overlap

More like this

✉ Message Thomas Roccia :verified:

🎤 Event / appearance with Thomas Roccia :verified: