shakedown.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A community for live music fans with roots in the jam scene. Shakedown Social is run by a team of volunteers (led by @clifff and @sethadam1) and funded by donations.

Administered by:

Server stats:

253
active users

#aisecurity

1 post1 participant0 posts today
Replied in thread

@dangoodin

Weird thing I observed in #infosec
There is an incredible amount of disinterest/contempt for #AI amongst many practitioners.

This contempt extends to willful ignorance about the subject.
q.v. "stochastic parrots/bullshit machines" etc.

Which, in a field with hundreds of millions of users, strikes me as highly unprofessional. Just the other day I read a blog post by a renown hacker (and likely earned a mute/block) "Why I don't use AI and you should not too".

Connor Leahy, CEO of #conjecture is one of the few credible folks in the field.

But to the question at hand.
The prompts are superbly sanitised.
In part by design, in part due to the fact that you are not connecting to a database but to a multidimensional vector data structure.

The #prompt is how you get in through the backdoor. Though I haven't looked into fuzzing, but I suspect because of the tech, the old #sqlinjection tek and similar will not work.

Long story short; It is literally impossible to build a secure #AI. By the virtue of the tech.
#promptengineering is the key to open the back door to the knowledge tree.

Then of course there are local models you can train on your own datasets. Including a stack of your old #2600magazine

📢 OWASP Ottawa August 2025 Meetup 📢

OWASP Ottawa is back from our summer break! Join us in person at the University of Ottawa for our next OWASP Ottawa meetup on August 20, 2025, where we’ll dive into not one, but two timely and impactful talks at the intersection of cybersecurity, AI, and real-world application security.

📅 Date: August 20, 2025
⏰ Time: 6:00 PM EST – Arrival, setup & pizza 🍕
6:30 PM EST – Technical Talks
📍 Location: 150 Louis-Pasteur Private, University of Ottawa, Room 117

🎙️ Talk 1: "Doing More with Less: An Adaptive, Label-Efficient Approach to Fraud Detection from Day One" with Bahar Afshar
👥 Speaker: Bahar Afshar, Master’s in Computer Science candidate with specialization in AI at University of Ottawa
Discover an innovative approach on how to detect financial fraud using adaptive, label-efficient AI approaches, even when labeled, fraudulent data is scarce. A must-see for those in finance, security, and AI research.

🎙️ Talk 2: "Beyond APIs: MCP Security for AI Integrations" with Harsh Makwana
👥 Speaker: Harsh Makwana, M.Eng, Aplication Security Consultant at Software Secured
Model Context Protocol (MCP) is becoming the standard for LLM integration with external tools, but this increasingly fast adoption rate is coming at the cost of missed security challenges. Learn the security strategies necessary to build hardened AI agents.

📺 Can’t join in person? We’ll livestream on YouTube on our channel: youtube.com/@OWASP_Ottawa

🔗 RSVP now: meetup.com/owasp-ottawa/events

Come learn, network, and grab some pizza 🍕 with Ottawa’s cybersecurity community!
.
.
.
.
.
.
.
.
#OWASP #Ottawa #Cybersecurity #InfoSec #Networking #AI #AISecurity #FraudDetection #MachineLearning

🚨 NEW Weekly Series Alert! 🚨

I’m excited to launch the Cybersecurity Weekly Roundup—a new series where I’ll share the top cybersecurity news stories every Friday.

Each week, I’ll curate the biggest incidents, emerging threats, critical vulnerabilities, and key industry insights—all from trusted cybersecurity sources like CISA, MITRE, The Hacker News, and more.

🛡️ Whether you're a cybersecurity pro, IT leader, or just security-curious, this roundup will help you:

Stay ahead of ransomware trends

Monitor critical vulnerabilities and patch releases

Learn about new threat actor campaigns

Track shifts in AI, ICS/OT, and post-quantum security

Every article includes a concise, expert-written summary designed to save you time and deliver actionable insights.

👉 Check out the first edition on the blog today!
🔗 weblog.kylereddoch.me/2025/07/

Follow me for weekly updates and stay cyber-resilient! 🔒

weblog.kylereddoch.me🛡️ Welcome to the Cybersecurity Weekly Roundup - Kyle's Tech Korner
More from CybersecKyle

Hello World! #introduction

Work in cybersec for 25+ years. Big OSS proponent.

Latest projects:

VectorSmuggle is acomprehensive proof-of-concept demonstrating vector-based data exfiltration techniques in AI/ML environments. This project illustrates potential risks in RAG systems and provides tools and concepts for defensive analysis.
github.com/jaschadub/VectorSmu

SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks (aka MCP Rug Pulls).
github.com/ThirdKeyAI/SchemaPin

GitHubGitHub - jaschadub/VectorSmuggle: Testing platform for covert data exfiltration techniques where sensitive documents are embedded into vector representations and tunneled out under the guise of legitimate RAG operations — bypassing traditional security controls and evading detection through semantic obfuscation.Testing platform for covert data exfiltration techniques where sensitive documents are embedded into vector representations and tunneled out under the guise of legitimate RAG operations — bypassing...

Microsoft Copilot for SharePoint just made recon a whole lot easier. 🚨
 
One of our Red Teamers came across a massive SharePoint, too much to explore manually. So, with some careful prompting, they asked Copilot to do the heavy lifting...
 
It opened the door to credentials, internal docs, and more.
 
All without triggering access logs or alerts.
 
Copilot is being rolled out across Microsoft 365 environments, often without teams realising Default Agents are already active.
 
That’s a problem.
 
Jack, our Head of Red Team, breaks it down in our latest blog post, including what you can do to prevent it from happening in your environment.
 
📌Read it here: pentestpartners.com/security-b

Man, this whole AI hype train... Yeah, sure, the tools are definitely getting sharper and faster, no doubt about it. But an AI pulling off a *real* pentest? Seriously doubt that's happening anytime soon. Let's be real: automated scans are useful, but they just aren't the same beast as a genuine penetration test.

Honestly, I think security needs to be woven right into the fabric of a company from the get-go. It can't just be an afterthought you tack on when alarms are already blaring.

Now, don't get me wrong, AI definitely brings its own set of dangers – disinformation is a big one that springs to mind. But here's the thing: we absolutely *have* to get our heads around these tools and figure them out. If we don't keep pace, we risk becoming irrelevant pretty quick.

So, curious to hear what you all think – where do the greatest pitfalls lie with AI in the security field? What keeps you up at night?