Ning Li

This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.

The paper introduces ADR, a novel, production-proven detection system that provides high-fidelity security monitoring for AI agents operating via the Model Context Protocol, significantly outperforming existing state-of-the-art baselines.

DREAM-R is a novel framework that significantly enhances speculative reasoning in large multimodal models by optimizing draft generation alignment, introducing a robust verification mechanism, and enabling fully parallel execution.

The paper introduces PokerSkill, a novel framework that successfully enables Large Language Models (LLMs) to play expert-level poker by grounding their choices using human-designed, rule-based poker skills, achieving competitive performance without requiring specialized training or complex solvers.

The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgetting and enhancing robustness.