arXiv subjects

Qian Xiong

Publications and source records attributed to Qian Xiong.

11 recordsLinked to original sources

arXiv2026

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected instructions often lack clear semantic boundaries from the surrounding context, making them difficult to identify. To address these issues, we propose InstruCoT, a model enhancement method for PI defense that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning, enabling LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. We evaluate InstruCoT across three critical dimensions: Behavior Deviation, Privacy Leakage, and Harmful Output. Experimental results across four LLMs demonstrate that InstruCoT significantly outperforms baselines in all dimensions while maintaining utility performance without degradation

cs.AI↗

arXiv2026

Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectories

LLMs have advanced tool-using agents for real-world applications, yet they often lead to unexpected behaviors or results. Beyond obvious failures, the subtle issue of "intent deviation" severely hinders reliable evaluation and performance improvement. Existing post-training methods generally leverage either real system samples or virtual data simulated by LLMs. However, the former is costly due to reliance on hand-crafted user requests, while the latter suffers from distribution shift from the real tools in the wild. Additionally, both methods lack negative samples tailored to intent deviation scenarios, hindering effective guidance on preference learning. We introduce RISE, a "Real-to-Virtual" method designed to mitigate intent deviation. Anchoring on verified tool primitives, RISE synthesizes virtual trajectories and generates diverse negative samples through mutation on critical parameters. With synthetic data, RISE fine-tunes backbone LLMs via the two-stage training for intent alignment. Evaluation results demonstrate that data synthesized by RISE achieve promising results in eight metrics covering user requires, execution trajectories and agent responses. Integrating with training, RISE achieves an average 35.28% improvement in Acctask (task completion) and 23.27% in Accintent (intent alignment), outperforming SOTA baselines by 1.20--42.09% and 1.17--54.93% respectively.

cs.AI↗

arXiv2025

AI and Jobs: Has the Inflection Point Arrived? Evidence from an Online Labor Platform

This study investigates how artificial intelligence (AI) influences various online labor markets (OLMs) over time. Employing the Difference-in-Differences method, we discovered two distinct scenarios following ChatGPT's launch: displacement effects featuring reduced work volume and earnings, exemplified by translation & localization OLM; productivity effects featuring increased work volume and earnings, exemplified by web development OLM. To understand these opposite effects in a unified framework, we developed a Cournot competition model to identify an inflection point for each market. Before this point, human workers benefit from AI enhancements; beyond this point, human workers would be replaced. Further analyzing the progression from ChatGPT 3.5 to 4.0, we found three effect scenarios, reinforcing our inflection point conjecture. Heterogeneous analyses reveal that U.S. web developers tend to benefit more from ChatGPT's launch compared to their counterparts in other regions. Experienced translators seem more likely to exit the market than less experienced translators.

cs.AI↗

arXiv2025

Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation

Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods perform inadequately in large-scale application-level software code generation, failing to ensure reasonable orga- nizational structures of project code and making it difficult to maintain the code generation process. To address this, this paper envisions a Knowledge-Guided Application-Level Code Generation framework named KGACG, which aims to trans- form software requirements specification and architectural design document into executable code through a collaborative closed- loop of the Code Organization & Planning Agent (COPA), Coding Agent (CA), and Testing Agent (TA), combined with a feedback mechanism. We demonstrate the collaborative process of the agents in KGACG in a Java Tank Battle game case study while facing challenges. KGACG is dedicated to advancing the automation of application-level software development.

cs.SE↗

arXiv2025

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models

Prompt-based adversarial attacks have become an effective means to assess the robustness of large language models (LLMs). However, existing approaches often treat prompts as monolithic text, overlooking their structural heterogeneity-different prompt components contribute unequally to adversarial robustness. Prior works like PromptRobust assume prompts are value-neutral, but our analysis reveals that complex, domain-specific prompts with rich structures have components with differing vulnerabilities. To address this gap, we introduce PromptAnatomy, an automated framework that dissects prompts into functional components and generates diverse, interpretable adversarial examples by selectively perturbing each component using our proposed method, ComPerturb. To ensure linguistic plausibility and mitigate distribution shifts, we further incorporate a perplexity (PPL)-based filtering mechanism. As a complementary resource, we annotate four public instruction-tuning datasets using the PromptAnatomy framework, verified through human review. Extensive experiments across these datasets and five advanced LLMs demonstrate that ComPerturb achieves state-of-the-art attack success rates. Ablation studies validate the complementary benefits of prompt dissection and PPL filtering. Our results underscore the importance of prompt structure awareness and controlled perturbation for reliable adversarial robustness evaluation in LLMs. Code and data are available at https://github.com/Yujiaaaaa/PACP.

cs.CL↗

arXiv2025

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems

The emergence of the tool agent paradigm has broadened the capability boundaries of the Large Language Model (LLM), enabling it to complete more complex tasks. However, the effectiveness of this paradigm is limited due to the issue of parameter failure during its execution. To explore this phenomenon and propose corresponding suggestions, we first construct a parameter failure taxonomy in this paper. We derive five failure categories from the invocation chain of a mainstream tool agent. Then, we explore the correlation between three different input sources and failure categories by applying 15 input perturbation methods to the input. Experimental results show that parameter name hallucination failure primarily stems from inherent LLM limitations, while issues with input sources mainly cause other failure patterns. To improve the reliability and effectiveness of tool-agent interactions, we propose corresponding improvement suggestions, including standardizing tool return formats, improving error feedback mechanisms, and ensuring parameter consistency.

cs.SE↗

arXiv2024

gECC: A GPU-based high-throughput framework for Elliptic Curve Cryptography

Elliptic Curve Cryptography (ECC) is an encryption method that provides security comparable to traditional techniques like Rivest-Shamir-Adleman (RSA) but with lower computational complexity and smaller key sizes, making it a competitive option for applications such as blockchain, secure multi-party computation, and database security. However, the throughput of ECC is still hindered by the significant performance overhead associated with elliptic curve (EC) operations. This paper presents gECC, a versatile framework for ECC optimized for GPU architectures, specifically engineered to achieve high-throughput performance in EC operations. gECC incorporates batch-based execution of EC operations and microarchitecture-level optimization of modular arithmetic. It employs Montgomery's trick to enable batch EC computation and incorporates novel computation parallelization and memory management techniques to maximize the computation parallelism and minimize the access overhead of GPU global memory. Also, we analyze the primary bottleneck in modular multiplication by investigating how the user codes of modular multiplication are compiled into hardware instructions and what these instructions' issuance rates are. We identify that the efficiency of modular multiplication is highly dependent on the number of Integer Multiply-Add (IMAD) instructions. To eliminate this bottleneck, we propose techniques to minimize the number of IMAD instructions by leveraging predicate registers to pass the carry information and using addition and subtraction instructions (IADD3) to replace IMAD instructions. Our results show that, for ECDSA and ECDH, gECC can achieve performance improvements of 5.56x and 4.94x, respectively, compared to the state-of-the-art GPU-based system. In a real-world blockchain application, we can achieve performance improvements of 1.56x, compared to the state-of-the-art CPU-based system.

cs.CR↗

arXiv2023

Expectile-based conditional tail moments with covariates

Expectile, as the minimizer of an asymmetric quadratic loss function, is a coherent risk measure and is helpful to use more information about the distribution of the considered risk. In this paper, we propose a new risk measure by replacing quantiles by expectiles, called expectile-based conditional tail moment, and focus on the estimation of this new risk measure as the conditional survival function of the risk, given the risk exceeding the expectile and given a value of the covariates, is heavy tail. Under some regular conditions, asymptotic properties of this new estimator are considered. The extrapolated estimation of the conditional tail moments is also investigated. These results are illustrated both on simulated data and on a real insurance data.

stat.ME↗

arXiv2023

MixDehazeNet : Mix Structure Block For Image Dehazing Network

Image dehazing is a typical task in the low-level vision field. Previous studies verified the effectiveness of the large convolutional kernel and attention mechanism in dehazing. However, there are two drawbacks: the multi-scale properties of an image are readily ignored when a large convolutional kernel is introduced, and the standard series connection of an attention module does not sufficiently consider an uneven hazy distribution. In this paper, we propose a novel framework named Mix Structure Image Dehazing Network (MixDehazeNet), which solves two issues mentioned above. Specifically, it mainly consists of two parts: the multi-scale parallel large convolution kernel module and the enhanced parallel attention module. Compared with a single large kernel, parallel large kernels with multi-scale are more capable of taking partial texture into account during the dehazing phase. In addition, an enhanced parallel attention module is developed, in which parallel connections of attention perform better at dehazing uneven hazy distribution. Extensive experiments on three benchmarks demonstrate the effectiveness of our proposed methods. For example, compared with the previous state-of-the-art methods, MixDehazeNet achieves a significant improvement (42.62dB PSNR) on the SOTS indoor dataset. The code is released in https://github.com/AmeryXiong/MixDehazeNet.

cs.CV↗

arXiv2023

Uniform convergence rates of skew-normal extremes

Let $M_n=\max \left(X_1, X_2, \ldots, X_n \right)$ denote the partial maximum of an independent and identically distributed skew-normal random sequence. In this paper, the rate of uniform convergence of skew-normal extremes is derived. It is shown that with optimal normalizing constants the convergence rate of $\left(M_{n}-b_n\right)/a_n$ to its ultimate extreme value distribution is proportional to $1/\log n$.

math.PR↗

arXiv2018

Principal components analysis of regularly varying functions

The paper is concerned with asymptotic properties of the principal components analysis of functional data. The currently available results assume the existence of the fourth moment. We develop analogous results in a setting which does not require this assumption. Instead, we assume that the observed functions are regularly varying. We derive the asymptotic distribution of the sample covariance operator and of the sample functional principal components. We obtain a number of results on the convergence of moments and almost sure convergence. We apply the new theory to establish the consistency of the regression operator in a functional linear model.

math.ST↗