Dawn Song
Professor of EECS, UC Berkeley | MacArthur Fellow | Pioneer of AI Security & Trustworthy ML
Professor of Electrical Engineering and Computer Sciences at UC Berkeley and MacArthur 'Genius' Fellow. One of the world's most cited researchers in computer security, AI security, and privacy-preserving machine learning. Pioneer of adversarial machine learning attacks and defenses, confidential computing for LLMs, verifiable agentic execution, and cryptographic guardrails for autonomous systems.
Areas of focus
Professional niches
Proof of Work
Confidential Computing & Privacy-Preserving LLM Inference Architectures
Engineered secure enclave and hardware-assisted cryptographic protocols ensuring user prompt embeddings and model weights remain provably encrypted during remote cloud GPU inference.
Enclave memory constraints introduce bandwidth overhead during large context-window KV cache allocation.
Context: NVIDIA H100 confidential computing enclaves and AMD SEV-SNP virtual machine attestation.
View missionAdversarial Attacks on Neural Networks in Physical and Digital Environments
Demonstrated that adversarial perturbations crafted via gradient-based optimization survive physical-world transformations (such as camera capture, lighting variations, and printing), exposing critical safety vulnerabilities in autonomous perception systems.
Defending against physical attacks often degrades clean-sample classification accuracy on subtle visual nuances.
Context: Inception and ResNet vision models subjected to physical adversarial stickers and perturbations.
View mission