Searcharxiv⌕ Search

arXiv subjects

Yiling He

Publications and source records attributed to Yiling He.

At least 19 recordsLinked to original sources
arXiv2026

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents

Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across agents.These results show greater variation across models than agent harness, while attacks remain highly successful across all tested harnesses.Our benchmark is released at: https://github.com/zjuicsr/ActBench.

cs.CR↗
arXiv2026

Malaika: Understanding Malware through Tri-Grounded Agentic Reasoning

Recent LLM-based systems have shown promising capabilities for security-focused code analysis. Malware understanding, however, poses a distinct challenge: analysts must reconstruct high-level malicious behaviors under partial observability from sparse, dispersed evidence intertwined with benign functionality. While static analysis can expose security-relevant signals, the central challenge is not merely identifying suspicious code, but determining whether the evidence sufficiently supports an auditable behavior-level conclusion. We formulate malware understanding as a grounded reasoning problem and argue that reliable behavior reconstruction requires three complementary forms of grounding. Domain grounding constrains how behavior hypotheses are generated and evaluated, semantics grounding localizes and connects supporting program evidence, and knowledge grounding supports behavioral attribution through externally verifiable threat knowledge. To study this hypothesis, we present Malaika, a multi-agent framework that operationalizes the three grounding mechanisms through analyst-inspired reasoning, tool-mediated evidence localization, and retrieval-based behavioral attribution. We instantiate Malaika for Android malware analysis and evaluate it on malware-understanding tasks. Results show that Malaika improves analysis quality over prior LLM-based malware-analysis frameworks and demonstrate that reliability depends not only on model capability but also on the reasoning process. In particular, comparisons against malware-analysis systems and frontier agentic frameworks show that grounding-aware reasoning produces more precise and auditable conclusions. Ablation studies further support the grounding hypothesis. These findings suggest that grounding-aware reasoning provides a principled foundation for reliable malware understanding and, more broadly, for evidence-grounded software analysis.

cs.CR↗
arXiv2026

TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks

Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heterogeneous threats, particularly between $\ell_p$-bounded and semantic attacks. Through first-order gradient analysis, we formalize this as gradient incompatibility and theoretically establish the necessity of decoupled optimization. We further reveal that these conflicting threats exhibit separable spectral characteristics in the frequency domain. Motivated by this observation, we propose Threat-aware Frequency Decoupling (TaFD), a two-stage defense framework that reformulates JAT as a frequency-domain divide-and-conquer paradigm. TaFD first discovers latent threat domains via unsupervised clustering of attack spectral prototypes and trains a lightweight classifier for inference-time threat domain identification. Conditioned on the prediction, TaFD employs a Frequency-Conditional Convolution that learns threat-domain-specific spectral masks and routes each sample to the corresponding expert, enforcing structural parameter separation and alleviating optimization conflicts. We validate TaFD on three representative image-classification benchmarks (CIFAR-10, CIFAR-100, and Tiny-ImageNet) and on two representative architectures (the convolutional ResNet and the hybrid-transformer MobileViT). Extensive results demonstrate that TaFD achieves more balanced robustness against heterogeneous attacks than existing JAT and frequency-domain baselines, improving average robust accuracy by approximately 11\% over the strongest baseline while maintaining leading clean accuracy.

cs.CV↗
arXiv2026

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines risk-conditioned evaluation, multi-objective trajectory scoring, reward-guided beam search, and reflection-based deep probing to identify high-value compromised contexts. We construct a 42-case benchmark spanning six vulnerability classes and seven operational scenarios, and evaluate nine target models using attack and utility grading scores. Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion, demonstrating that final-response evaluation is insufficient. The findings highlight the need for execution-centric security evaluation of agentic AI systems. Our code is released at: https://github.com/ZJUICSR/DeepTrap

cs.CR↗
arXiv2025

Esim: EVM Bytecode Similarity Detection Based on Stable-Semantic Graph

Decentralized finance (DeFi) is experiencing rapid expansion. However, prevalent code reuse and limited open-source contributions have introduced significant challenges to the blockchain ecosystem, including plagiarism and the propagation of vulnerable code. Consequently, an effective and accurate similarity detection method for EVM bytecode is urgently needed to identify similar contracts. Traditional binary similarity detection methods are typically based on instruction stream or control flow graph (CFG), which have limitations on EVM bytecode due to specific features like low-level EVM bytecode and heavily-reused basic blocks. Moreover, the highly-diverse Solidity Compiler (Solc) versions further complicate accurate similarity detection. Motivated by these challenges, we propose a novel EVM bytecode representation called Stable-Semantic Graph (SSG), which captures relationships between 'stable instructions' (special instructions identified by our study). Moreover, we implement a prototype, Esim, which embeds SSG into matrices for similarity detection using a heterogeneous graph neural network. Esim demonstrates high accuracy in SSG construction, achieving F1-scores of 100% for control flow and 95.16% for data flow, and its similarity detection performance reaches 96.3% AUC, surpassing traditional approaches. Our large-scale study, analyzing 2,675,573 smart contracts on six EVM-compatible chains over a one-year period, also demonstrates that Esim outperforms the SOTA tool Etherscan in vulnerability search.

cs.CR↗
arXiv2025

Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis

Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code representations shift. While continual learning (CL) offers a natural solution through sequential updates, most existing approaches rely on data replay or unconstrained updates, limiting their applicability and effectiveness in data-sensitive security environments. We propose RETROFIT, which regulates knowledge retention and adaptation with controlled forgetting at each update, without requiring historical data. Our key idea is to consolidate previously trained and newly fine-tuned models, serving as teachers of legacy and emergent knowledge, through retrospective-free parameter merging. Forgetting control is achieved by 1) constraining parameter changes to low-rank and sparse subspaces for approximate orthogonality, and 2) employing a confidence-guided arbitration mechanism to dynamically aggregate knowledge from both teachers. Our evaluation on two representative applications demonstrates that RETROFIT consistently mitigates forgetting while maintaining adaptability. In malware detection under temporal drift, it substantially improves the retention score, from 20.2% to 38.6% over CL baselines, and exceeds the oracle upper bound on new data. In binary summarization across decompilation levels, where analyzing stripped binaries is especially challenging, RETROFIT achieves over 2x the BLEU score of transfer learning used in prior work and surpasses all baselines in cross-representation generalization.

cs.LG↗
arXiv2025

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence. Traditional signature-based methods and learning-based XAI often fail to provide such support in a human-interpretable form. Large Language Models (LLMs) appear promising, yet their reliability for malware auditing remains unclear. Evaluation faces three challenges: (1) the lack of human-written behavioral ground truth; (2) real-world codebases that exceed current context limits; and (3) the lack of reliable mechanisms to verify whether generated claims are grounded in code evidence. These obstacles make benchmarking difficult and leave model capabilities and failure modes opaque. We introduce MalEval, a diagnostic framework for measuring the capability boundaries of LLMs in malware auditing. MalEval pairs real-world application codebases with expert-written audit reports to provide fine-grained behavior-level ground truth. It compresses large codebases into behavior-relevant program contexts through a context-driven intermediate representation that preserves call relations. Expert reports and model outputs are mapped, via constrained reasoning, into structured evidence chains linking code-level facts to high-level behaviors in a shared space. MalEval decomposes auditing into four stage-wise tasks, enabling each intermediate judgment to be verified under limited context windows. We evaluate seven LLMs and find that they rely on surface cues rather than verifiable evidence, struggle to compose dispersed facts into coherent attack chains, and are highly sensitive to context formulation. These findings shift attention from isolated outputs to reliable LLM and agentic workflows for malware auditing. MalEval is publicly available at https://github.com/ZhengXR930/MalEval.git

cs.CR↗
arXiv2025

Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models

Binary code similarity detection (BCSD) serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming at misleading the models to generate erroneous predictions. Prior works have explored various approaches to generating semantic-preserving variants, i.e., adversarial samples, to evaluate the robustness of the models against adversarial attacks. However, they have mainly relied on heuristic criteria or iterative greedy algorithms to locate salient code influencing the model output, failing to operate on a solid theoretical basis. Moreover, when processing programs with high complexities, such attacks tend to be time-consuming. In this work, we propose a novel optimization for adversarial attacks against BCSD models. In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range, i.e., the targeted attacks. Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries, thereby pinpointing the critical code snippet to apply semantic-preserving perturbations. The evaluation results demonstrate that compared with the state-of-the-art attacks, the proposed attacks achieve higher attack success rate in almost all scenarios, while also improving the efficiency and transferability. Our real-world case studies on vulnerability detection and classification further demonstrate the security implications of our attacks, highlighting the urgent need to further enhance the robustness of existing BCSD models.

cs.CR↗
arXiv2025

Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models

Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations. These issues, exacerbated by token limits, often cause models to miss vulnerability-related signals, thereby impairing effective learning. A key intuition is to enhance LMs with concise, information-rich context. Commit-based annotations offer precise, CWE-agnostic supervision, but are unavailable during inference, as they depend on historical code changes. Moreover, their extreme sparsity, often covering only a few lines, makes it difficult for LMs to process directly. In this paper, we propose FocusVul, a model-agnostic framework that improves LM-based vulnerability detection by learning to select sensitive context. FocusVul learns commit-based annotation patterns through hierarchical semantic modeling and generalizes them to identify line-level vulnerability-relevant regions during inference. It then extracts LM-oriented context via both dependency and execution flows surrounding selected regions, yielding semantically rich inputs for effective vulnerability detection. Experiments on real-world benchmarks show that FocusVul consistently outperforms heuristic-based and full-function fine-tuning approaches, improving classification performance by 164.04% and reducing FLOPs by 19.12% on average.

cs.SE↗
arXiv2025

On Benchmarking Code LLMs for Android Malware Analysis

Large Language Models (LLMs) have demonstrated strong capabilities in various code intelligence tasks. However, their effectiveness for Android malware analysis remains underexplored. Decompiled Android malware code presents unique challenges for analysis, due to the malicious logic being buried within a large number of functions and the frequent lack of meaningful function names. This paper presents CAMA, a benchmarking framework designed to systematically evaluate the effectiveness of Code LLMs in Android malware analysis. CAMA specifies structured model outputs to support key malware analysis tasks, including malicious function identification and malware purpose summarization. Built on these, it integrates three domain-specific evaluation metrics (consistency, fidelity, and semantic relevance), enabling rigorous stability and effectiveness assessment and cross-model comparison. We construct a benchmark dataset of 118 Android malware samples from 13 families collected in recent years, encompassing over 7.5 million distinct functions, and use CAMA to evaluate four popular open-source Code LLMs. Our experiments provide insights into how Code LLMs interpret decompiled code and quantify the sensitivity to function renaming, highlighting both their potential and current limitations in malware analysis.

cs.CR↗
arXiv2025

Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustness

Color constancy estimates illuminant chromaticity to correct color-biased images. Recently, Deep Neural Network-driven Color Constancy (DNNCC) models have made substantial advancements. Nevertheless, the potential risks in DNNCC due to the vulnerability of deep neural networks have not yet been explored. In this paper, we conduct the first investigation into the impact of a key factor in color constancy-brightness-on DNNCC from a robustness perspective. Our evaluation reveals that several mainstream DNNCC models exhibit high sensitivity to brightness despite their focus on chromaticity estimation. This sheds light on a potential limitation of existing DNNCC models: their sensitivity to brightness may hinder performance given the widespread brightness variations in real-world datasets. From the insights of our analysis, we propose a simple yet effective brightness robustness enhancement strategy for DNNCC models, termed BRE. The core of BRE is built upon the adaptive step-size adversarial brightness augmentation technique, which identifies high-risk brightness variation and generates augmented images via explicit brightness adjustment. Subsequently, BRE develops a brightness-robustness-aware model optimization strategy that integrates adversarial brightness training and brightness contrastive loss, significantly bolstering the brightness robustness of DNNCC models. BRE is hyperparameter-free and can be integrated into existing DNNCC models, without incurring additional overhead during the testing phase. Experiments on two public color constancy datasets-ColorChecker and Cube+-demonstrate that the proposed BRE consistently enhances the illuminant estimation performance of existing DNNCC models, reducing the estimation error by an average of 5.04% across six mainstream DNNCC models, underscoring the critical role of enhancing brightness robustness in these models.

cs.CV↗
arXiv2025

LAMD: Context-driven Android Malware Detection and Classification with LLMs

The rapid growth of mobile applications has escalated Android malware threats. Although there are numerous detection methods, they often struggle with evolving attacks, dataset biases, and limited explainability. Large Language Models (LLMs) offer a promising alternative with their zero-shot inference and reasoning capabilities. However, applying LLMs to Android malware detection presents two key challenges: (1)the extensive support code in Android applications, often spanning thousands of classes, exceeds LLMs' context limits and obscures malicious behavior within benign functionality; (2)the structural complexity and interdependencies of Android applications surpass LLMs' sequence-based reasoning, fragmenting code analysis and hindering malicious intent inference. To address these challenges, we propose LAMD, a practical context-driven framework to enable LLM-based Android malware detection. LAMD integrates key context extraction to isolate security-critical code regions and construct program structures, then applies tier-wise code reasoning to analyze application behavior progressively, from low-level instructions to high-level semantics, providing final prediction and explanation. A well-designed factual consistency verification mechanism is equipped to mitigate LLM hallucinations from the first tier. Evaluation in real-world settings demonstrates LAMD's effectiveness over conventional detectors, establishing a feasible basis for LLM-driven malware analysis in dynamic threat landscapes.

cs.CR↗
arXiv2024

ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs

Recent advancements have led to the widespread adoption of code-oriented large language models (Code LLMs) for programming tasks. Despite their success in deployment, their security research is left far behind. This paper introduces a new attack paradigm: (automatic) external prompt injection against Code LLMs, where attackers generate concise, non-functional induced perturbations and inject them within a victim's code context. These induced perturbations can be disseminated through commonly used dependencies (e.g., packages or RAG's knowledge base), manipulating Code LLMs to achieve malicious objectives during the code completion process. Compared to existing attacks, this method is more realistic and threatening: it does not necessitate control over the model's training process, unlike backdoor attacks, and can achieve specific malicious objectives that are challenging for adversarial attacks. Furthermore, we propose ShadowCode, a simple yet effective method that automatically generates induced perturbations based on code simulation to achieve effective and stealthy external prompt injection. ShadowCode designs its perturbation optimization objectives by simulating realistic code contexts and employs a greedy optimization approach with two enhancement modules: forward reasoning enhancement and keyword-based perturbation design. We evaluate our method across 13 distinct malicious objectives, generating 31 threat cases spanning three popular programming languages. Our results demonstrate that ShadowCode successfully attacks three representative open-source Code LLMs (achieving up to a 97.9% attack success rate) and two mainstream commercial Code LLM-integrated applications (with over 90% attack success rate) across all threat cases, using only a 12-token non-functional induced perturbation. The code is available at https://github.com/LianPing-cyber/ShadowCodeEPI.

cs.CR↗
arXiv2024

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution

Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.

cs.CR↗
arXiv2024

Combating Concept Drift with Explanatory Detection and Adaptation for Android Malware Classification

Machine learning-based Android malware classifiers achieve high accuracy in stationary environments but struggle with concept drift. The rapid evolution of malware, especially with new families, can depress classification accuracy to near-random levels. Previous research has largely centered on detecting drift samples, with expert-led label revisions on these samples to guide model retraining. However, these methods often lack a comprehensive understanding of malware concepts and provide limited guidance for effective drift adaptation, leading to unstable detection performance and high human labeling costs. To combat concept drift, we propose DREAM, a novel system that improves drift detection and establishes an explanatory adaptation process. Our core idea is to integrate classifier and expert knowledge within a unified model. To achieve this, we embed malware explanations (or concepts) within the latent space of a contrastive autoencoder, while constraining sample reconstruction based on classifier predictions. This approach enhances classifier retraining in two key ways: 1) capturing the target classifier's characteristics to select more effective samples in drift detection and 2) enabling concept revisions that extend the classifier's semantics to provide stronger guidance for adaptation. Additionally, DREAM eliminates reliance on training data during real-time drift detection and provides a behavior-based drift explainer to support concept revision. Our evaluation shows that DREAM effectively improves the drift detection accuracy and reduces the expert analysis effort in adaptation across different malware datasets and classifiers. Notably, when updating a widely-used Drebin classifier, DREAM achieves the same accuracy with 76.6% fewer newly labeled samples compared to the best existing methods.

cs.CR↗
arXiv2023

RetouchUAA: Unconstrained Adversarial Attack via Image Retouching

Deep Neural Networks (DNNs) are susceptible to adversarial examples. Conventional attacks generate controlled noise-like perturbations that fail to reflect real-world scenarios and hard to interpretable. In contrast, recent unconstrained attacks mimic natural image transformations occurring in the real world for perceptible but inconspicuous attacks, yet compromise realism due to neglect of image post-processing and uncontrolled attack direction. In this paper, we propose RetouchUAA, an unconstrained attack that exploits a real-life perturbation: image retouching styles, highlighting its potential threat to DNNs. Compared to existing attacks, RetouchUAA offers several notable advantages. Firstly, RetouchUAA excels in generating interpretable and realistic perturbations through two key designs: the image retouching attack framework and the retouching style guidance module. The former custom-designed human-interpretability retouching framework for adversarial attack by linearizing images while modelling the local processing and retouching decision-making in human retouching behaviour, provides an explicit and reasonable pipeline for understanding the robustness of DNNs against retouching. The latter guides the adversarial image towards standard retouching styles, thereby ensuring its realism. Secondly, attributed to the design of the retouching decision regularization and the persistent attack strategy, RetouchUAA also exhibits outstanding attack capability and defense robustness, posing a heavy threat to DNNs. Experiments on ImageNet and Place365 reveal that RetouchUAA achieves nearly 100\% white-box attack success against three DNNs, while achieving a better trade-off between image naturalness, transferability and defense robustness than baseline attacks.

cs.CV↗
arXiv2023

Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case generation. Despite their great potential, language models for code intelligence (LM4Code) are susceptible to potential pitfalls, which hinder realistic performance and further impact their reliability and applicability in real-world deployment. Such challenges drive the need for a comprehensive understanding - not just identifying these issues but delving into their possible implications and existing solutions to build more reliable language models tailored to code intelligence. Based on a well-defined systematic research approach, we conducted an extensive literature review to uncover the pitfalls inherent in LM4Code. Finally, 67 primary studies from top-tier venues have been identified. After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems. We developed a comprehensive classification scheme that dissects pitfalls across four crucial aspects: data collection and labeling, system design and learning, performance evaluation, and deployment and maintenance. Through this study, we aim to provide a roadmap for researchers and practitioners, facilitating their understanding and utilization of LM4Code in reliable and trustworthy ways.

cs.SE↗
arXiv2023

FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis

Deep learning classifiers achieve state-of-the-art performance in various risk detection applications. They explore rich semantic representations and are supposed to automatically discover risk behaviors. However, due to the lack of transparency, the behavioral semantics cannot be conveyed to downstream security experts to reduce their heavy workload in security analysis. Although feature attribution (FA) methods can be used to explain deep learning, the underlying classifier is still blind to what behavior is suspicious, and the generated explanation cannot adapt to downstream tasks, incurring poor explanation fidelity and intelligibility. In this paper, we propose FINER, the first framework for risk detection classifiers to generate high-fidelity and high-intelligibility explanations. The high-level idea is to gather explanation efforts from model developer, FA designer, and security experts. To improve fidelity, we fine-tune the classifier with an explanation-guided multi-task learning strategy. To improve intelligibility, we engage task knowledge to adjust and ensemble FA methods. Extensive evaluations show that FINER improves explanation quality for risk detection. Moreover, we demonstrate that FINER outperforms a state-of-the-art tool in facilitating malware analysis.

cs.CR↗