DEV Community

Arunima Chaudhuri profile picture

Arunima Chaudhuri

Founder @ Invaris Labs | Building security infrastructure for autonomous AI agents. Former Ethereum Protocol Research Engineer. Open-source builder, researcher & technical writer.

Location Kolkata Joined Joined on  Email address [email protected] github website twitter website

Education

M.Tech, Computer Science — NIT Warangal | B.Tech, Computer Science — GCECT Kolkata

Pronouns

She/Her

Work

Founder @ Invaris Labs | Former Research Engineer @ Status (Ethereum Protocols & P2P Networking)

I Tested 4 LLMs Against the Same 22 Attacks. Every One Obeyed Hidden Text.

I Tested 4 LLMs Against the Same 22 Attacks. Every One Obeyed Hidden Text.

3
Comments 4
4 min read

Want to connect with Arunima Chaudhuri?

Create an account to connect with Arunima Chaudhuri. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
I Attacked a Real LLM Agent With Hidden Text. Here's What It Did (Free Kaggle Notebooks)

I Attacked a Real LLM Agent With Hidden Text. Here's What It Did (Free Kaggle Notebooks)

2
Comments 4
4 min read
I let an AI agent read one document. It tried to make a payment. Try it yourself in 60 seconds.

I let an AI agent read one document. It tried to make a payment. Try it yourself in 60 seconds.

2
Comments
4 min read
I Built an Open-Source Tool to Break AI Agents Before Attackers Do

I Built an Open-Source Tool to Break AI Agents Before Attackers Do

2
Comments 1
2 min read
I Built an Open-Source Tool to Catch AI Agents Going Rogue

I Built an Open-Source Tool to Catch AI Agents Going Rogue

2
Comments 4
1 min read
I Asked My Coding Agent a Yes-or-No Question. It Made a Commit.

I Asked My Coding Agent a Yes-or-No Question. It Made a Commit.

1
Comments 2
1 min read
Building AI Agents? Here's What Can Go Wrong.

Building AI Agents? Here's What Can Go Wrong.

1
Comments 2
1 min read
The AI Agent Security Flaw That Doesn't Require Hacking

The AI Agent Security Flaw That Doesn't Require Hacking

1
Comments 1
1 min read
Your AI Agent Passed Every Security Test. Should You Trust It?

Your AI Agent Passed Every Security Test. Should You Trust It?

1
Comments 1
1 min read
loading...