Yaswanth B

Final-year B.E. student specializing in AI/ML Security & LLM Red Teaming, with hands-on experience building layered defenses for LLM, RAG, and agentic AI systems - prompt injection & jailbreak testing, RBAC, context isolation, and audit logging - grounded in the OWASP Top 10 for LLM Applications and MITRE ATLAS adversarial ML threat framework, alongside Web/API penetration testing and secure SDLC practices. Skilled across LangChain, LangGraph, CrewAI, and AutoGen, with working knowledge of Python, adversarial ML concepts, and cloud security (AWS, Azure). Published researcher, CEH (v13) certified, and OWASP community speaker.

Bug Bounty Researcher — Web & LLM Security at Bug Bounty Programs (2026-01 – Present)

• Discovered and responsibly disclosed 3+ valid vulnerabilities (XSS, injection flaws) through private bug bounty programs.
• Identified issues leading to potential account takeover and data exposure; reported with a remediation-focused approach.

Cybersecurity Intern at Prompt Infotech (2025-06 – 2025-07)

• Performed vulnerability assessments and network traffic analysis using ethical hacking methodologies.
• Documented security weaknesses into actionable remediation reports under a Cyber Crime Investigator's mentorship; recognized for outstanding performance.

B.E. in Computer & Communication Engineering – Sri Eshwar College of Engineering (2023-01 – 2027-12)