Karthik BhaskarThoughts on trustworthy AI, adversarial ML, LLM security, and applied research.https://kbhaskar.com/The OWASP Top 10 for LLMs: What Actually Mattershttps://kbhaskar.com/blog/owasp-top-10-llm-2025/https://kbhaskar.com/blog/owasp-top-10-llm-2025/OWASP released its 2025 Top 10 for LLM Applications. Having built and secured LLM systems, here's which vulnerabilities actually bite and which ones are noise.Tue, 14 Apr 2026 11:23:56 GMTThe GCG Attack: Three Years Later, We Still Haven't Solved Ithttps://kbhaskar.com/blog/gcg-adversarial-attacks-llms/https://kbhaskar.com/blog/gcg-adversarial-attacks-llms/In 2023, a single paper broke the safety alignment of every major LLM. Three years and dozens of defenses later, the core problem remains unsolved. Here's what happened.Wed, 08 Apr 2026 09:30:00 GMTHello World: A New Beginninghttps://kbhaskar.com/blog/hello-world/https://kbhaskar.com/blog/hello-world/Introducing my new website and what to expect from this blog - thoughts on trustworthy AI, adversarial ML, and building reliable AI systems.Fri, 03 Apr 2026 14:15:00 GMT