Ilia Shumailov

Exploiting a vulnerability in LLM APIs allows attackers to extract proprietary reasoning and sensitive data without directly breaching the more capable models.

Repurposing retired GPUs can cut costs dramatically, but without clean energy, it risks quadrupling carbon emissions for LLM inference.

LLM-powered honeypots can trick even frontier models into longer interactions than rule-based systems, all while costing less to run.

Dynamic quantization, a widely adopted optimization for efficient ML serving, can leak your data to adversaries sharing the same batch.

Cracking DNNs is now easier than ever: Kraken extracts parameters from GPU Tensor Cores via near-field EM attacks and even sniffs LLM weights from a meter away.