Bo Ma

The paper introduces TIGER, a GPU-accelerated framework that significantly speeds up high-precision evaluation of nonlinear layers for encrypted LLM inference using TFHE.

BodhiPromptShield is a policy-aware framework that mediates prompt privacy by detecting sensitive data and replacing it with secure placeholders across multiple stages (retrieval, memory, tools) to prevent privacy leakage in LLM/VLM agents.

The paper argues that zero-day attacks primarily exploit undisclosed vulnerabilities rather than exhibiting novel behaviors, advocating for vulnerability-centric detection methods over purely behavior-based approaches.

The paper proposes IntraGuard, a black-box, venue-agnostic defense framework that embeds hidden instructions into manuscripts via PDF structure to disrupt AI-generated peer reviews, achieving up to 84% defense success.

GESR introduces a graph-based framework that reconstructs edge semantics from local structural context to detect stealthy malicious communications using only benign training data, achieving high performance on standard datasets.

This paper systematically investigates how various plasticity interventions affect the vulnerability of deep reinforcement learning agents to backdoor attacks, finding that most interventions mitigate threats while one specific intervention exacerbates them.