Aryaman Behera Email & Phone Number

“Our customer support AI just started giving cooking recipes instead of tech support. We're trending on X," your CTO mutters, coffee going cold.“But the guardrails were titanium-grade," your head of AI stammers."But we manually tested it against every prompt injection in our book," your security lead protestsYou feel your stomach drop as you contemplate the inevitable board meetings, customer notifications, and potential regulatory investigations ahead.Here's the reality: 89% of organizations are using or exploring LLMs, yet only 5% feel confident in securing them. AI security isn't optional anymore – it's essential.To secure your AI systems without killing innovation, you need a strategy:-> Identify the attack surface: AI systems face unique vulnerabilities - from prompt injection to training data poisoning. Most security teams are equipped to handle traditional cyber threats, but AI-specific attacks require specialized knowledge and tools. Understanding where your AI systems are vulnerable is the first step to securing them.-> Build security guardrails, intelligently: While it's tempting to lock down your AI systems completely, this can severely limit their functionality. The key is implementing smart boundaries - like input validation, output filtering, and runtime monitoring - that protect against attacks while preserving performance. You can't defend against what you don't understand, so comprehensive testing and monitoring are crucial.-> Implement continuous red-teaming: Traditional penetration testing isn't enough for AI systems. You need ongoing adversarial testing that evolves with your models. This includes testing for data extraction, prompt injection, and model manipulation attempts. Remember, it only takes one successful attack to compromise your entire system.Attack is the best form of defense. So, we're building Repello AI to help organizations secure their GenAI applications from an attacker's perspective. We've been fortunate to work with leading Fortune 500 companies and AI unicorns, helping them safeguard their AI applications against novel AI-specific threats.I built & sold my first company in junior year of IIT Roorkee. I served as the captain of InfoSecIITR - now one of the top undergrad CTF teams in the world. I've been in cybersecurity for around 7 years - red teaming, CTFs, ethical hacking and now building my second company Repello AI, backed by General Catalyst, pi Ventures and prominent angel investors. Need more info on how we can help you?Head to https://repello.ai/

Listed skills include Web Development and C++.

• 

  Indian Institute Of Technology, Roorkee

  Bachelor Of Technology - Btech