arXiv subjects

Wenbo Guo

Publications and source records attributed to Wenbo Guo.

At least 55 records · Page 3Linked to original sources

arXiv2025

IntelliRadar: A Comprehensive Platform to Pinpoint Malicious Package Information from Cyber Intelligence

Malicious packages in public registries pose serious threats to software supply chain security. While current software component analysis (SCA) tools rely on databases like OSV and Snyk to detect these threats, these databases suffer from delayed updates and incomplete coverage. However, they miss intelligence from unstructured sources like social media and developer forums, where new threats are often first reported. This delay extends the lifecycle of malicious packages and increases risks for downstream users. To address this, we developed a novel and comprehensive approach to construct a platform IntelliRadar to collect disclosed malicious package names from unstructured web content. Specifically, by exhaustively searching and snowballing the public sources of malicious package names, and incorporating large language models (LLMs) with domain-specialized Least to Most prompts, IntelliRadar ensures comprehensive collection of historical and current disclosed malicious package names from diverse unstructured sources. As a result, we constructed a comprehensive malicious package database containing 34,313 malicious NPM and PyPI package names. Our evaluation shows that IntelliRadar achieves high performance (97.91% precision) on malicious package intelligence extraction. Compared to existing databases, IntelliRadar identifies 7,542 more malicious package names than OSV and 12,684 more than Snyk. Furthermore, 76.6% of NPM components and 70.3% of PyPI components in IntelliRadar were collected earlier than in Snyk's database. IntelliRadar is also more cost-efficient, with a cost of $0.003 per piece of malicious package intelligence and only $7 per month for continuous monitoring. Furthermore, we identified and received confirmation for 1,981 malicious packages in downstream package manager mirror registries through the IntelliRadar.

cs.SE↗

arXiv2025

Demystifying Network Foundation Models

This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs) that focuses on hidden representations analysis rather than pure downstream task performance. Different from existing efforts, we analyze the models through a three-part evaluation: Embedding Geometry Analysis to assess representation space utilization, Metric Alignment Assessment to measure correspondence with domain-expert features, and Causal Sensitivity Testing to evaluate robustness to protocol perturbations. Using five diverse network datasets spanning controlled and real-world environments, we evaluate four state-of-the-art NFMs, revealing that they all exhibit significant anisotropy, inconsistent feature sensitivity patterns, an inability to separate the high-level context, payload dependency, and other properties. Our work identifies numerous limitations across all models and demonstrates that addressing them can significantly improve model performance (by up to +0.35 $F_1$ score without architectural changes).

cs.LG↗

arXiv2025

HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning

Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforward, these methods have limited diversity in generated tests and cannot provide enough debugging information. We propose HarnessLLM, a two-stage training pipeline that enables LLMs to write harness code for testing. Particularly, LLMs generate code that synthesizes inputs and validates the observed outputs, allowing complex test cases and flexible output validation such as invariant checking. To achieve this, we train LLMs with SFT followed by RLVR with a customized reward design. Experiments show that HarnessLLM outperforms input-output-based testing in bug finding and testing strategy diversity. HarnessLLM further benefits the code generation performance through test-time scaling with our generated test cases as inference-phase validation. Our code is available at https://github.com/UCSB-NLP-Chang/HarnessLLM.git.

cs.SE↗

arXiv2025

BlockScan: Detecting Anomalies in Blockchain Transactions

We propose BlockScan, a customized Transformer for anomaly detection in blockchain transactions. Unlike existing methods that rely on rule-based systems or directly apply off-the-shelf large language models (LLMs), BlockScan introduces a series of customized designs to effectively model the unique data structure of blockchain transactions. First, a blockchain transaction is multi-modal, containing blockchain-specific tokens, texts, and numbers. We design a novel modularized tokenizer to handle these multi-modal inputs, balancing the information across different modalities. Second, we design a customized masked language modeling mechanism for pretraining the Transformer architecture, incorporating RoPE embedding and FlashAttention for handling longer sequences. Finally, we design a novel anomaly detection method based on the model outputs. We further provide theoretical analysis for the detection method of our system. Extensive evaluations on Ethereum and Solana transactions demonstrate BlockScan's exceptional capability in anomaly detection while maintaining a low false positive rate. Remarkably, BlockScan is the only method that successfully detects anomalous transactions on Solana with high accuracy, whereas all other approaches achieved very low or zero detection recall scores. This work sets a new benchmark for applying Transformer-based approaches in blockchain data analysis.

cs.CR↗

arXiv2025

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities and risks of CodeGen models. However, progress on the blue teaming side remains limited, as developing defense requires effective semantic understanding to differentiate the unsafe from the safe. To fill in this gap, we propose BlueCodeAgent, an end-to-end blue teaming agent enabled by automated red teaming. Our framework integrates both sides: red teaming generates diverse risky instances, while the blue teaming agent leverages these to detect previously seen and unseen risk scenarios through constitution and code analysis with agentic integration for multi-level defense. Our evaluation across three representative code-related tasks--bias instruction detection, malicious instruction detection, and vulnerable code detection--shows that BlueCodeAgent achieves significant gains over the base models and safety prompt-based defenses. In particular, for vulnerable code detection tasks, BlueCodeAgent integrates dynamic analysis to effectively reduce false positives, a challenging problem as base models tend to be over-conservative, misclassifying safe code as unsafe. Overall, BlueCodeAgent achieves an average 12.7\% F1 score improvement across four datasets in three tasks, attributed to its ability to summarize actionable constitutions that enhance context-aware risk detection. We demonstrate that the red teaming benefits the blue teaming by continuously identifying new vulnerabilities to enhance defense performance.

cs.SE↗

arXiv2025

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving

Assessing the safety of autonomous driving (AD) systems against security threats, particularly backdoor attacks, is a stepping stone for real-world deployment. However, existing works mainly focus on pixel-level triggers that are impractical to deploy in the real world. We address this gap by introducing a novel backdoor attack against the end-to-end AD systems that leverage one or more other vehicles' trajectories as triggers. To generate precise trigger trajectories, we first use temporal logic (TL) specifications to define the behaviors of attacker vehicles. Configurable behavior models are then used to generate these trajectories, which are quantitatively evaluated and iteratively refined based on the TL specifications. We further develop a negative training strategy by incorporating patch trajectories that are similar to triggers but are designated not to activate the backdoor. It enhances the stealthiness of the attack and refines the system's responses to trigger scenarios. Through extensive experiments on 5 offline reinforcement learning (RL) driving agents with 6 trigger patterns and target action combinations, we demonstrate the flexibility and effectiveness of our proposed attack, showing the under-exploration of existing end-to-end AD systems' vulnerabilities to such trajectory-based backdoor attacks.

cs.CR↗

arXiv2025

Evolaris: A Roadmap to Self-Evolving Software Intelligence Management

In recent years, the landscape of software threats has become significantly more dynamic and distributed. Security vulnerabilities are no longer discovered and shared only through formal channels such as public vulnerability databases or vendor advisories. Increasingly, criti- cal threat information emerges informally through blogs, social media, developer forums, open source repositories, and even underground com- munities. To this end, capturing such intelligence in a timely manner is essential for maintaining situational awareness and enabling prompt security responses. However, this remains a complex challenge due to the fragmented nature of data sources and the technical difficulty of collecting, parsing, mapping, and validating information at scale. To ad- dress this, we propose Evolaris, a self-evolving software intelligence sys- tem built on a multi-agent framework. Evolaris is designed to support a full-stack workflow, where agents operate independently but coordinate through shared context to perform tasks such as information discovery, reasoning, gap completion, validation, and risk detection. This archi- tecture enables the platform to learn from new inputs, refine its internal knowledge, and adapt to emerging threat patterns over time, which could continuously improve the precision, timeliness, and scalability of software threat analysis, and offers a sustainable foundation for proactive secu- rity decision-making and strengthens the broader ecosystem of security threat understanding.

cs.SE↗

arXiv2025

SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI

Existing benchmarks for evaluating the security risks and capabilities (e.g., vulnerability detection) of code-generating large language models (LLMs) face several key limitations: (1) limited coverage of risk and capabilities; (2) reliance on static evaluation metrics such as LLM judgments or rule-based detection, which lack the precision of dynamic analysis; and (3) a trade-off between data quality and benchmark scale. To address these challenges, we introduce a general and scalable benchmark construction framework that begins with manually validated, high-quality seed examples and expands them via targeted mutations. Our approach provides a comprehensive suite of artifacts so the benchmark can support comprehensive risk assessment and security capability evaluation using dynamic metrics. By combining expert insights with automated generation, we strike a balance between manual effort, data quality, and benchmark scale. Applying this framework to Python, C/C++, and Java, we build SeCodePLT, a dataset of more than 5.9k samples spanning 44 CWE-based risk categories and three security capabilities. Compared with state-of-the-art benchmarks, SeCodePLT offers broader coverage, higher data fidelity, and substantially greater scale. We use SeCodePLT to evaluate leading code LLMs and agents, revealing their strengths and weaknesses in both generating secure code and identifying or fixing vulnerabilities.

cs.CR↗

arXiv2025

MiqroForge: An Intelligent Workflow Platform for Quantum-Enhanced Computational Chemistry

The connect-fill-run workflow paradigm, widely adopted in mature software engineering, accelerates collaborative development. However, computational chemistry, computational materials science, and computational biology face persistent demands for multi-scale simulations constrained by simplistic platform designs. We present MiqroForge, an intelligent cross-scale platform integrating quantum computing capabilities. By combining AI-driven dynamic resource scheduling with an intuitive visual interface, MiqroForge significantly lowers entry barriers while optimizing computational efficiency. The platform fosters a collaborative ecosystem through shared node libraries and data repositories, thereby bridging practitioners across classical and quantum computational domains.

physics.chem-ph↗

arXiv2025

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts. Existing red-teaming approaches for privacy leakage either rely on manual efforts or focus solely on system prompt extraction, making them ineffective for severe risks of training data leakage. We propose LeakAgent, a novel black-box red-teaming framework for LLM privacy leakage. Our framework trains an open-source LLM through reinforcement learning as the attack agent to generate adversarial prompts for both training data extraction and system prompt extraction. To achieve this, we propose a novel reward function to provide effective and fine-grained rewards and design novel mechanisms to balance exploration and exploitation during learning and enhance the diversity of adversarial prompts. Through extensive evaluations, we first show that LeakAgent significantly outperforms existing rule-based approaches in training data extraction and automated methods in system prompt leakage. We also demonstrate the effectiveness of LeakAgent in extracting system prompts from real-world applications in OpenAI's GPT Store. We further demonstrate LeakAgent's effectiveness in evading the existing guardrail defense and its helpfulness in enabling better safety alignment. Finally, we validate our customized designs through a detailed ablation study. We release our code here https://github.com/rucnyz/LeakAgent.

cs.CR↗

arXiv2025

BandFuzz: An ML-powered Collaborative Fuzzing Framework

Collaborative fuzzing combines multiple individual fuzzers and dynamically chooses appropriate combinations for different programs. Unlike individual fuzzers that rely on specific assumptions, collaborative fuzzing relaxes assumptions on target programs, providing robust performance across various programs. However, existing collaborative fuzzing frameworks face challenges including additional computational resource requirements and inefficient resource allocation among fuzzers. To tackle these challenges, we present BANDFUZZ, an ML-powered collaborative fuzzing framework that outperforms individual fuzzers without requiring additional computational resources. The key contribution of BANDFUZZ lies in its novel resource allocation algorithm driven by our proposed multi-armed bandits model. Different from greedy methods in existing frameworks, BANDFUZZ models the long-term impact of individual fuzzers, enabling discovery of globally optimal collaborative strategies. We propose a novel fuzzer evaluation method that assesses not only code coverage but also the fuzzer's capability of solving difficult branches. Finally, we integrate a real-time seed synchronization mechanism and implementation-wise optimizations to improve fuzzing efficiency and stability. Through extensive experiments on Fuzzbench and Fuzzer Test Suite, we show that BANDFUZZ outperforms state-of-the-art collaborative fuzzing framework autofz and widely used individual fuzzers. We verify BANDFUZZ's key designs through comprehensive ablation study. Notably, we demonstrate BANDFUZZ's effectiveness in real-world bug detection by analyzing results of a worldwide fuzzing competition, where BANDFUZZ won first place.

cs.CR↗

arXiv2025

PromptArmor: Simple yet Effective Prompt Injection Defenses

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than the intended task provided by the user. In this paper, we present PromptArmor, a simple yet effective defense against prompt injection attacks. Specifically, PromptArmor prompts an off-the-shelf LLM to detect and remove potential injected prompts from the input before the agent processes it. Our results show that PromptArmor can accurately identify and remove injected prompts. For example, using GPT-4o, GPT-4.1, or o4-mini, PromptArmor achieves both a false positive rate and a false negative rate below 1% on the AgentDojo benchmark. Moreover, after removing injected prompts with PromptArmor, the attack success rate drops to below 1%. We also demonstrate PromptArmor's effectiveness against adaptive attacks and explore different strategies for prompting an LLM. We recommend that PromptArmor be adopted as a standard baseline for evaluating new defenses against prompt injection attacks.

cs.CR↗

arXiv2025

Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In this paper, we reveal a subtle yet impactful weakness in these aligned models. We find that simply appending multiple end of sequence (eos) tokens can cause a phenomenon we call context segmentation, which effectively shifts both harmful and benign inputs closer to the refusal boundary in the hidden space. Building on this observation, we propose a straightforward method to BOOST jailbreak attacks by appending eos tokens. Our systematic evaluation shows that this strategy significantly increases the attack success rate across 8 representative jailbreak techniques and 16 open-source LLMs, ranging from 2B to 72B parameters. Moreover, we develop a novel probing mechanism for commercial APIs and discover that major providers such as OpenAI, Anthropic, and Qwen do not filter eos tokens, making them similarly vulnerable. These findings highlight a hidden yet critical blind spot in existing alignment and content filtering approaches. We call for heightened attention to eos tokens' unintended influence on model behaviors, particularly in production systems. Our work not only calls for an input-filtering based defense, but also points to new defenses that make refusal boundaries more robust and generalizable, as well as fundamental alignment techniques that can defend against context segmentation attacks.

cs.AI↗

arXiv2025

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents

The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these powerful features also introduce a critical security risk: indirect prompt injection, a sophisticated attack vector that compromises the core of these agents, the LLM, by manipulating contextual information rather than direct user prompts. In this work, we propose a generic black-box fuzzing framework, AgentVigil, designed to automatically discover and exploit indirect prompt injection vulnerabilities across diverse LLM agents. Our approach starts by constructing a high-quality initial seed corpus, then employs a seed selection algorithm based on Monte Carlo Tree Search (MCTS) to iteratively refine inputs, thereby maximizing the likelihood of uncovering agent weaknesses. We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o, respectively, nearly doubling the performance of baseline attacks. Moreover, AgentVigil exhibits strong transferability across unseen tasks and internal LLMs, as well as promising results against defenses. Beyond benchmark evaluations, we apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.

cs.CR↗

arXiv2025

PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification

Recent research builds various patching agents that combine large language models (LLMs) with non-ML tools and achieve promising results on the state-of-the-art (SOTA) software patching benchmark, SWE-bench. Based on how to determine the patching workflows, existing patching agents can be categorized as agent-based planning methods, which rely on LLMs for planning, and rule-based planning methods, which follow a pre-defined workflow. At a high level, agent-based planning methods achieve high patching performance but with a high cost and limited stability. Rule-based planning methods, on the other hand, are more stable and efficient but have key workflow limitations that compromise their patching performance. In this paper, we propose PatchPilot, an agentic patcher that strikes a balance between patching efficacy, stability, and cost-efficiency. PatchPilot proposes a novel rule-based planning workflow with five components: reproduction, localization, generation, validation, and refinement (where refinement is unique to PatchPilot). We introduce novel and customized designs to each component to optimize their effectiveness and efficiency. Through extensive experiments on the SWE-bench benchmarks, PatchPilot shows a superior performance than existing open-source methods while maintaining low cost (less than 1$ per instance) and ensuring higher stability. We also conduct a detailed ablation study to validate the key designs in each component. Our code is available at https://github.com/ucsb-mlsec/PatchPilot.

cs.RO↗

arXiv2025

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions. Existing defenses against IPI have significant limitations: either require essential model training resources, lack effectiveness against sophisticated attacks, or harm the normal utilities. We present MELON (Masked re-Execution and TooL comparisON), a novel IPI defense. Our approach builds on the observation that under a successful attack, the agent's next action becomes less dependent on user tasks and more on malicious tasks. Following this, we design MELON to detect attacks by re-executing the agent's trajectory with a masked user prompt modified through a masking function. We identify an attack if the actions generated in the original and masked executions are similar. We also include three key designs to reduce the potential false positives and false negatives. Extensive evaluation on the IPI benchmark AgentDojo demonstrates that MELON outperforms SOTA defenses in both attack prevention and utility preservation. Moreover, we show that combining MELON with a SOTA prompt augmentation defense (denoted as MELON-Aug) further improves its performance. We also conduct a detailed ablation study to validate our key designs. Code is available at https://github.com/kaijiezhu11/MELON.

cs.CR↗

arXiv2025

F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI

Recent research has developed a number of eXplainable AI (XAI) techniques, such as gradient-based approaches, input perturbation-base methods, and black-box explanation methods. While these XAI techniques can extract meaningful insights from deep learning models, how to properly evaluate them remains an open problem. The most widely used approach is to perturb or even remove what the XAI method considers to be the most important features in an input and observe the changes in the output prediction. This approach, although straightforward, suffers the Out-of-Distribution (OOD) problem as the perturbed samples may no longer follow the original data distribution. A recent method RemOve And Retrain (ROAR) solves the OOD issue by retraining the model with perturbed samples guided by explanations. However, using the model retrained based on XAI methods to evaluate these explainers may cause information leakage and thus lead to unfair comparisons. We propose Fine-tuned Fidelity (F-Fidelity), a robust evaluation framework for XAI, which utilizes i) an explanation-agnostic fine-tuning strategy, thus mitigating the information leakage issue, and ii) a random masking operation that ensures that the removal step does not generate an OOD input. We also design controlled experiments with state-of-the-art (SOTA) explainers and their degraded version to verify the correctness of our framework. We conduct experiments on multiple data modalities, such as images, time series, and natural language. The results demonstrate that F-Fidelity significantly improves upon prior evaluation metrics in recovering the ground-truth ranking of the explainers. Furthermore, we show both theoretically and empirically that, given a faithful explainer, F-Fidelity metric can be used to compute the sparsity of influential input components, i.e., to extract the true explanation size.

cs.LG↗

arXiv2025

3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly

Industrial anomaly detection achieves progress thanks to datasets such as MVTec-AD and VisA. However, they suffer from limitations in terms of the number of defect samples, types of defects, and availability of real-world scenes. These constraints inhibit researchers from further exploring the performance of industrial detection with higher accuracy. To this end, we propose a new large-scale anomaly detection dataset called 3CAD, which is derived from real 3C production lines. Specifically, the proposed 3CAD includes eight different types of manufactured parts, totaling 27,039 high-resolution images labeled with pixel-level anomalies. The key features of 3CAD are that it covers anomalous regions of different sizes, multiple anomaly types, and the possibility of multiple anomalous regions and multiple anomaly types per anomaly image. This is the largest and first anomaly detection dataset dedicated to 3C product quality control for community exploration and development. Meanwhile, we introduce a simple yet effective framework for unsupervised anomaly detection: a Coarse-to-Fine detection paradigm with Recovery Guidance (CFRG). To detect small defect anomalies, the proposed CFRG utilizes a coarse-to-fine detection paradigm. Specifically, we utilize a heterogeneous distillation model for coarse localization and then fine localization through a segmentation model. In addition, to better capture normal patterns, we introduce recovery features as guidance. Finally, we report the results of our CFRG framework and popular anomaly detection methods on the 3CAD dataset, demonstrating strong competitiveness and providing a highly challenging benchmark to promote the development of the anomaly detection field. Data and code are available: https://github.com/EnquanYang2022/3CAD.

cs.CV↗