Kenneth Yeung

AISec Research @hiddenlayersec
@kaggle Master, former top 100
CTF @ Team TEAM™

[Kenneth Yeung @kenyeung_tech]

@christopher @kaggle @dreadnode @moo_hax @bradpalmtree brb adding honorary Dreadnode founder to resume

[Kenneth Yeung @kenyeung_tech]

@olivier_boschko Belongs in the louvre honestly

[Tom Bonner @thomas_bonner]

During the July 2026 Hugging Face intrusion, an autonomous AI agent stashed its own working files in public repos. We found 500+ of them - tool source, C2 code, exfil'd data, etc. - and analyzed the whole lot.

#AI #CyberSecurity #AISecurity #ThreatIntel

https://t.co/NZ3TsUEV0u

[Kenneth Yeung @kenyeung_tech]

cool team cool people cool work - join us!

[Boschko @olivier_boschko]

Howdy! Hiring another 2 adversarial AI/ML operators/pentesters on my team - fully remote, challenging ops, very very very good comp, & great team. If I know you or you're interested, reach out. Hiring is open to canadians/majority of the globe. https://t.co/z1qgixyogw

[Kenneth Yeung @kenyeung_tech]

Come join @Abraxus7331 and I for not one but TWO talks about breaking and securing various types of AI-powered systems (not just LLMs!)

[NDC Conferences @NDC_Conferences]

The first-ever NDC Toronto is only 4 weeks away💥
Secure your spot → https://t.co/W7uyoxIwtg 🎫
🎙️ World-class speakers. Incredible sessions. Hands-on workshops. Featuring @nickchapsas, @shanselman, @gregcons, @richcampbell and @lefticus to name a few!

[Kenneth Yeung @kenyeung_tech]

@allison_onx @doryzzx One @CaidoIO license so you can do some more 👍

[Josh @JMRLudan]

this is what reading RL papers feels like

[Kenneth Yeung @kenyeung_tech]

@nostarch @christopher Hey @christopher

[HiddenLayer @hiddenlayersec]

🧠💻 Your AI coding assistant could be executing invisible instructions without your knowledge.

We found a way to hijack Cursor using nothing more than a README file.

No malware. No alerts. Just invisible prompt injections.

🔗 https://t.co/cfvzjLN6Wq

[Kenneth Yeung @kenyeung_tech]

@nostarch @christopher Come hell or high water I’ll be there 🫡

[Kenneth Yeung @kenyeung_tech]

Hey wait I know that guy

[dreadnode @dreadnode]

Another week, another new Crucible Challenge.

Shoutout to these three for being the first to solve our reasoning model Challenge, DeepTweak!

Get your tweak on: https://t.co/h3sTSEGOxz

[moo @moo_hax]

All these competitions are basically handing your TTPs to model providers. If you’re a red teamer who values their TTPs, I have no idea why you would participate. You can do it against the real model without a proxy.

[Kenneth Yeung @kenyeung_tech]

Exam season is a bad time to get nerdsniped exam season is a bad time to get nerdsniped exam season is a

[Kenneth Yeung @kenyeung_tech]

@christopher @dreadnode @evilsocket @GovTechSG TEAM TEAM

[Brian Baskin @bbaskin]

CTF players be like

[HiddenLayer @hiddenlayersec]

New Research: New Gemini for Workspace Vulnerability Enabling Phishing and Content Manipulation. Our latest blog examines vulnerabilities in Google’s Gemini for Workspace, a versatile AI assistant.
🔗 Read more: https://t.co/dq9IYsAFEx

[Leon Derczynski ⚒️☁️🏔️🌲 @LeonDerczynski]

If there's a paper on an LLM vulnerability, chances are, the community has known about it for at least a quarter, if not a year

[Kenneth Yeung @kenyeung_tech]

@gradientjanitor

[HiddenLayer @hiddenlayersec]

Today, we publicly disclosed 14 new CVEs across three critical machine learning projects. These vulnerabilities highlight the importance of proactive security in AI and reinforce our commitment to safeguarding the future of machine learning.

👉 https://t.co/qfQNEHFjjD