Chen Zhang

The paper introduces a kill-chain canary methodology to diagnose prompt injection vulnerabilities across multi-stage LLM pipelines, revealing that write-node placement and document format are critical safety weak points.

The paper proposes RPM-Net, a novel framework using a reciprocal point mechanism and adversarial margin constraints to achieve superior detection of unknown network security threats in imbalanced multi-class environments.

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are distinct from inherent LLM flaws.

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.

The paper introduces MT-JailBench, a modular framework for evaluating multi-turn jailbreaks, demonstrating that controlling experimental components like prompt generation and resource budgets is crucial for fair comparison and understanding attack success.

The paper introduces GRIEF, a greybox fuzzer that discovers critical, concurrency-related vulnerabilities in LLM serving systems by treating timed multi-request traces as inputs, finding issues like cache isolation failures and cross-request contamination.

The paper proposes eSpat-B and eSpat+ systems to enable efficient and privacy-preserving distribution statistics analysis on massive, dynamic mobile spatial data.

VFEAgent is a novel multi-agent framework that automates the entire Finite Element Analysis (FEA) workflow, achieving high success rates in generating complete and physically valid simulations directly from multimodal inputs.

The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for large multimodal models.

The paper introduces a higher-order network framework to compare observed and simulated human mobility data, demonstrating that while synthetic data is promising, current simulation models have specific limitations regarding path-based movement patterns.

IstGPT introduces a novel LLM-based framework for real-time, fine-grained anomaly detection in complex industrial cyber-physical systems, achieving state-of-the-art performance across multiple benchmarks.