Yan Liu

This study estimates the true social cost of corporate data breaches by quantifying the direct financial and opportunity costs to victims, finding that these costs can significantly exceed corporate settlements, though the marginal social cost per victim appears to be declining over time.

This paper conducts the first real-world safety evaluation of the personal AI agent OpenClaw, demonstrating that its broad system access creates inherent vulnerabilities that significantly increase the attack success rate regardless of the underlying large language model.

LymphNode is a novel, post-hoc access control framework that protects Deep Neural Networks (DNNs) from model extraction and inversion attacks by enforcing a default-deny policy and selectively restoring utility only for authorized queries.

The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertainty in intermediate summaries, significantly improving long-horizon agent performance.

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improvements for agent behaviors and coordination.

CAREAgent is a novel agent designed for fine-grained clinical order generation, achieving significant performance improvements on unseen benchmarks by integrating structured reasoning and tool usage.

MViewRouter proposes a multi-view framework that internalizes geometric equivariance using a Multi-view Alternating Attention mechanism to improve generalization and stabilize training for combinatorial routing problems like TSP and CVRP.

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative examples, achieving significant performance gains with minimal latency.

This paper proposes ARTSN, a scheduling paradigm for autonomous real-time systems using time-sensitive networking, addressing volatility and absence challenges of self-triggered traffic.