@eneelou Profile picture

Eugene Neelou

@eneelou

Pioneer in AI Security, MLSecOps, AI Red Teaming | Industry Expert, Product Manager, Consultant | Co-founded an AI Safety startup, OWASP LLM Top 10

Similar User
Trustworthy ML Initiative (TrustML) photo

@trustworthy_ml

AI, Ethics, and Society Conference (AIES) photo

@AIESConf

ACM FAccT photo

@FAccTConference

Battista Biggio photo

@biggiobattista

Ram Shankar Siva Kumar photo

@ram_ssk

Yang Zhang photo

@realyangzhang

Florian Tramèr photo

@florian_tramer

Maura Pintor photo

@maurapintor

Pin-Yu Chen photo

@pinyuchenTW

Camlis Org photo

@CamlisOrg

Yizheng Chen photo

@surrealyz

Hyrum Anderson photo

@drhyrum

Reza Shokri photo

@rzshokri

Fabio Pierazzi photo

@fbpierazzi

Eugene Bagdasarian photo

@ebagdasa

Pinned

After coining the term MLSecOps in 2017, I'm finally presenting the best you ever saw introduction to MLSecOps, or DevSecOps for AI systems, with core principles, ML pipeline stages, and examples! Slides and Video: conf42.com/DevSecOps_2022… #AI #SecureAI #MLSecOps #DevSecOps


Quantum security means the controls are only working when you're looking at them.


Can't wait to see how we transition from trustworthy AI to zero-trust AI -- just like the shift from trustworthy computing to zero-trust security. P.S. Here's a 22-year-old column from Bill Gates introducing Trustworthy Computing: wired.com/2002/01/bill-g…


Very often it's unlikely I'll find good content when a title includes both "Security for AI" and "AI for Security."


Cast your vote and help OWASP choose the next Top 10 risks for LLM security! The voting process will also eliminate some entries, keeping only the top 10 -- so choose wisely. Only a few days left! Contribute your opinion via this Google Form: docs.google.com/forms/d/e/1FAI…


Are most AI Red Teams just glorified QA testers? Coming from classic cyber red teaming, I feel very frustrated about how the term has been adopted in the AI industry. Curious how many times the definition will drift before the scope of work and responsibilities are finalized?


Is it Chinese or American research if 10 Chinese PhD students at a U.S. university publish an AI security paper?


Your little weekend project! Help us at OWASP refine the Top 10 for LLM Security. Share your feedback about the new top 10 candidates here: docs.google.com/forms/d/e/1FAI… The deadline is Sunday, June 30. Your opinion matters!


Eugene Neelou Reposted

Superintelligence is within reach. Building safe superintelligence (SSI) is the most important technical problem of our​​ time. We've started the world’s first straight-shot SSI lab, with one goal and one product: a safe superintelligence. It’s called Safe Superintelligence…


Eugene Neelou Reposted

So Apple has introduced a new system called “Private Cloud Compute” that allows your phone to offload complex (typically AI) tasks to specialized secure devices in the cloud. I’m still trying to work out what I think about this. So here’s a thread. 1/


Eugene Neelou Reposted

Due to a security incident, we strongly suggest you rotate any tokens or keys you use in secrets for HF Spaces: huggingface.co/docs/hub/en/sp…. We have already proactively revoked a number of HF tokens and are working with cybersecurity forensic specialists to investigate the issue as…


I find it ironic that Master of Laws degrees are called LLMs.


100K consultants will be sharing customer data with ChatGPT What a gift to the AI security market! Isn't it? techcrunch.com/2024/05/29/ope…


Here is how China recruits hackers for $5,000 a month

Tweet Image 1

Look how many AI agents are waiting to be compromised!

Tweet Image 1

I found it quite surprising that many people didn't get the reference to my role and employer at @GISECGlobal

Tweet Image 1

I predict that LLM system prompts will become public and formalized just like how most websites have robots.txt files Robots file reference: twitter . com / robots . txt System prompt reference: @AnthropicAI's Amanda Askell

Tweet Image 1

The real reason why ChatGPT was banned in Italy

Tweet Image 1

Eugene Neelou Reposted

BREAKING: OpenAI Announces GPT-5 As New CEO

Tweet Image 1

Eugene Neelou Reposted

Holy crap! THIRTY EIGHT TERABYTES of leaked AI Training data from @Windows including internal chat history 😭 wiz.io/blog/38-teraby…


Loading...

Something went wrong.


Something went wrong.