Chen Liu

The paper proposes AdaBFL, a multi-layer defensive adaptive aggregation method that enhances Byzantine-robust federated learning by adaptively adjusting defense weights to counter complex poisoning attacks.

The paper introduces GRID, an end-to-end framework that significantly improves the construction of security knowledge graphs from cyber threat intelligence by replacing unstable LLM-based supervision with a stable, scripted task-bank reward system.

The paper proposes interaction-layer antidistillation watermarks by embedding behavioral markers into the system prompt, which successfully track knowledge distillation even when paraphrasing attackers strip traditional token-level signals.

ChainCaps introduces a novel runtime capability budgeting system that prevents 'permission laundering' in complex tool-using agents, significantly reducing attack success rates while maintaining benign functionality.

The paper introduces Causal Editing (CODE), a new paradigm that improves knowledge updates in LLMs by grounding fact injection in causal narratives, drastically reducing self-refutation rates.

The paper introduces Archon, a unified, fully pretrained multimodal model that addresses the challenge of generating holistic digital humans by integrating seven modalities (including text, audio, motion, and visual content) into a single autoregressive framework.

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world knowledge as a latent graph.

This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the financial sector.

The paper introduces HomeFlow, a verifiable data flywheel that procedurally generates high-quality, multi-turn training data for smart home agents, achieving state-of-the-art performance on smart home tasks.

The paper introduces SMH-Bench, a comprehensive benchmark built on a simulator to rigorously test LLM agents' ability to perform complex, environment-grounded reasoning and actions in realistic smart-home scenarios.

The paper introduces and analyzes cross-session stored prompt injection, demonstrating that persistent system state transforms prompt injection from a temporary model-level threat into a long-lived, system-level vulnerability in agentic systems.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.