Rajkumar Buyya

RAG systems may expose sensitive information through various attack vectors, challenging the trustworthiness of AI-generated outputs.

A multi-agent framework boosts diagnostic precision by over 11% while tackling critical failure modes in AI-driven healthcare.

DFL-AA eliminates link-quality distortion in decentralized federated learning, leading to more accurate and timely model updates even in lossy environments.

Turns out, the security vulnerabilities in LLM fine-tuning are a moving target: attacks that worked on older models don't always work on newer ones, and even seemingly benign data can break safety alignment.

LLM scaling bottlenecks demand a shift towards cloud-native architectures and distributed systems, unlocking potential gains from serverless inference and quantum computing.

Like the periodic table for chemistry, a new "periodic framework" promises to bring order and predictability to the chaotic world of distributed computing.

Quantum reinforcement learning gets a distributed boost, achieving 10% better performance in multi-agent environments by distributing the learning load across multiple quantum agents.

Federated reinforcement learning can now handle heterogeneous, adversarial IoT environments with near-zero deadline violations, thanks to a novel decentralized framework that transfers knowledge across silos.

Overcome the scalability bottleneck of GNN-based root cause analysis in edge computing by cascading subnetworks over clustered service graphs, achieving near-constant inference latency without sacrificing accuracy.

Optimizing UAV routes and edge computing together slashes wildfire monitoring response times by up to 84% while shrinking drone fleets by over 40%.

Circuit cutting introduces substantial end-to-end overheads in quantum neural network training, with reconstruction dominating per-query time, but surprisingly, test accuracy and robustness can be preserved or even improved.