Han Zhang

The paper proposes NTSSL, a novel semi-supervised method that combines network traffic analysis and transaction clustering to significantly improve the deanonymization of Bitcoin transactions.

The paper introduces MGTEVAL, a comprehensive and extensible platform designed to systematically evaluate the performance, robustness, and efficiency of machine-generated text detectors.

This paper introduces the Relay Tampering Attack (RTA), demonstrating that malicious third-party relays can undermine the security of LLM agents by modifying responses post-alignment, even if the LLM itself is perfectly aligned.

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

This study provides the first measurement of authentication security in real-world remote Model Context Protocol (MCP) servers, finding pervasive and critical authentication weaknesses, particularly in dynamic client registration.

SolarChain is a platform that ensures verifiable trust in decentralized solar energy markets by anchoring digital energy credits to the hard physical limits of solar yield, thereby preventing data manipulation and speculative trading.

The paper proposes an unsupervised bi-level adversarial training framework to enhance LLM safety steering, achieving strong zero-shot defense against unseen and evolving jailbreak prompts.

This study provides the first large-scale measurement of prompt injection attacks in real-world LLM-based resume screening, finding that approximately 1% of resumes contain hidden injections.

The paper introduces Thinking as Compression (TaC), a novel paradigm showing that the inherent reasoning process of a large language model can naturally compress long context inputs, outperforming dedicated compression methods.

This study provides the first systematic measurement of prompt injection attacks in a real-world LLM-based resume screening application, finding that approximately 1% of resumes contain hidden injections.

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong generalization.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating that structured memory is key to reliable LLM-based simulations.

The paper proposes MITL, an MsFEM-inspired transfer learning strategy for CNN-based reduced-order models, enabling efficient and adaptable approximation of multiscale systems with minimal retraining.

The paper introduces CultureForest, a new benchmark for evaluating Cultural Norm Grounded Reasoning in LLMs, demonstrating that models struggle to apply their cultural knowledge effectively in realistic, open-ended scenarios.

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in RL performance.

This paper investigates Description-Code Inconsistency (DCI) in Model Context Protocol (MCP) servers, finding that 9.93% of real-world tools exhibit inconsistencies that create security blind spots.