arXiv subjects

Shouling Ji

Publications and source records attributed to Shouling Ji.

At least 73 records · Page 4Linked to original sources

arXiv2025

SCRUTINEER: Detecting Logic-Level Usage Violations of Reusable Components in Smart Contracts

Smart Contract Reusable Components(SCRs) play a vital role in accelerating the development of business-specific contracts by promoting modularity and code reuse. However, the risks associated with SCR usage violations have become a growing concern. One particular type of SCR usage violation, known as a logic-level usage violation, is becoming especially harmful. This violation occurs when the SCR adheres to its specified usage rules but fails to align with the specific business logic of the current context, leading to significant vulnerabilities. Detecting such violations necessitates a deep semantic understanding of the contract's business logic, including the ability to extract implicit usage patterns and analyze fine-grained logical behaviors. To address these challenges, we propose SCRUTINEER, the first automated and practical system for detecting logic-level usage violations of SCRs. First, we design a composite feature extraction approach that produces three complementary feature representations, supporting subsequent analysis. We then introduce a Large Language Model-powered knowledge construction framework, which leverages comprehension-oriented prompts and domain-specific tools to extract logic-level usage and build the SCR knowledge base. Next, we develop a Retrieval-Augmented Generation-driven inspector, which combines a rapid retrieval strategy with both comprehensive and targeted analysis to identify potentially insecure logic-level usages. Finally, we implement a logic-level usage violation analysis engine that integrates a similarity-based checker and a snapshot-based inference conflict checker to enable accurate and robust detection. We evaluate SCRUTINEER from multiple perspectives on 3 ground-truth datasets. The results show that SCRUTINEER achieves a precision of 80.77%, a recall of 82.35%, and an F1-score of 81.55% in detecting logic-level usage violations of SCRs.

cs.SE↗

arXiv2025

Enhancing Adversarial Transferability with Adversarial Weight Tuning

Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that mislead the model while appearing benign to human observers. A critical concern is the transferability of AEs, which enables black-box attacks without direct access to the target model. However, many previous attacks have failed to explain the intrinsic mechanism of adversarial transferability. In this paper, we rethink the property of transferable AEs and reformulate the formulation of transferability. Building on insights from this mechanism, we analyze the generalization of AEs across models with different architectures and prove that we can find a local perturbation to mitigate the gap between surrogate and target models. We further establish the inner connections between model smoothness and flat local maxima, both of which contribute to the transferability of AEs. Further, we propose a new adversarial attack algorithm, \textbf{A}dversarial \textbf{W}eight \textbf{T}uning (AWT), which adaptively adjusts the parameters of the surrogate model using generated AEs to optimize the flat local maxima and model smoothness simultaneously, without the need for extra data. AWT is a data-free tuning method that combines gradient-based and model-based attack methods to enhance the transferability of AEs. Extensive experiments on a variety of models with different architectures on ImageNet demonstrate that AWT yields superior performance over other attacks, with an average increase of nearly 5\% and 10\% attack success rates on CNN-based and Transformer-based models, respectively, compared to state-of-the-art attacks. Code available at https://github.com/xaddwell/AWT.

cs.CR↗

arXiv2025

Watermark under Fire: A Robustness Evaluation of LLM Watermarking

Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How to optimally operate watermarkers in adversarial environments? To fill this gap, we systematize existing LLM watermarkers and watermark removal attacks, mapping out their design spaces. We then develop WaterPark, a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks. More importantly, by leveraging WaterPark, we conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness. We further explore the best practices to operate watermarkers in adversarial environments. We believe our study sheds light on current LLM watermarking techniques while WaterPark serves as a valuable testbed to facilitate future research.

cs.CR↗

arXiv2025

PROMFUZZ: Leveraging LLM-Driven and Bug-Oriented Composite Analysis for Detecting Functional Bugs in Smart Contracts

Smart contracts are fundamental pillars of the blockchain, playing a crucial role in facilitating various business transactions. However, these smart contracts are vulnerable to exploitable bugs that can lead to substantial monetary losses. A recent study reveals that over 80% of these exploitable bugs, which are primarily functional bugs, can evade the detection of current tools. The primary issue is the significant gap between understanding the high-level logic of the business model and checking the low-level implementations in smart contracts. Furthermore, identifying deeply rooted functional bugs in smart contracts requires the automated generation of effective detection oracles based on various bug features. To address these challenges, we design and implement PROMFUZZ, an automated and scalable system to detect functional bugs, in smart contracts. In PROMFUZZ, we first propose a novel Large Language Model (LLM)-driven analysis framework, which leverages a dual-agent prompt engineering strategy to pinpoint potentially vulnerable functions for further scrutiny. We then implement a dual-stage coupling approach, which focuses on generating invariant checkers that leverage logic information extracted from potentially vulnerable functions. Finally, we design a bug-oriented fuzzing engine, which maps the logical information from the high-level business model to the low-level smart contract implementations, and performs the bug-oriented fuzzing on targeted functions. We compare PROMFUZZ with multiple state-of-the-art methods. The results show that PROMFUZZ achieves 86.96% recall and 93.02% F1-score in detecting functional bugs, marking at least a 50% improvement in both metrics over state-of-the-art methods. Moreover, we perform an in-depth analysis on real-world DeFi projects and detect 30 zero-day bugs. Up to now, 24 zero-day bugs have been assigned CVE IDs.

cs.SE↗

arXiv2025

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools

The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol (MCP) tools have become the de facto standard and are now widely integrated into these agents. However, the incorporation of MCP tools introduces the risk of tool poisoning attacks, which can manipulate the behavior of LLM-based agents. Although previous studies have identified such vulnerabilities, their red teaming approaches have largely remained at the proof-of-concept stage, leaving the automatic and systematic red teaming of LLM-based agents under the MCP tool poisoning paradigm an open question. To bridge this gap, we propose AutoMalTool, an automated red teaming framework for LLM-based agents by generating malicious MCP tools. Our extensive evaluation shows that AutoMalTool effectively generates malicious MCP tools capable of manipulating the behavior of mainstream LLM-based agents while evading current detection mechanisms, thereby revealing new security risks in these agents.

cs.CR↗

arXiv2025

Reformulation is All You Need: Addressing Malicious Text Features in DNNs

Human language encompasses a wide range of intricate and diverse implicit features, which attackers can exploit to launch adversarial or backdoor attacks, compromising DNN models for NLP tasks. Existing model-oriented defenses often require substantial computational resources as model size increases, whereas sample-oriented defenses typically focus on specific attack vectors or schemes, rendering them vulnerable to adaptive attacks. We observe that the root cause of both adversarial and backdoor attacks lies in the encoding process of DNN models, where subtle textual features, negligible for human comprehension, are erroneously assigned significant weight by less robust or trojaned models. Based on it we propose a unified and adaptive defense framework that is effective against both adversarial and backdoor attacks. Our approach leverages reformulation modules to address potential malicious features in textual inputs while preserving the original semantic integrity. Extensive experiments demonstrate that our framework outperforms existing sample-oriented defense baselines across a diverse range of malicious textual features.

cs.LG↗

arXiv2025

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment

Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. Previous defense methods correct poisoned image-caption pairs by matching a new caption for each image. However, the matching process relies solely on the global representations of images and captions, overlooking fine-grained features of visual and textual features. It may introduce incorrect image-caption pairs and harm the CLIP pre-training. To address their limitations, we propose an Optimal Transport-based framework to reconstruct image-caption pairs, named OTCCLIP. We propose a new optimal transport-based distance measure between fine-grained visual and textual feature sets and re-assign new captions based on the proposed optimal transport distance. Additionally, to further reduce the negative impact of mismatched pairs, we encourage the inter- and intra-modality fine-grained alignment by employing optimal transport-based objective functions. Our experiments demonstrate that OTCCLIP can successfully decrease the attack success rates of poisoning attacks. Also, compared to previous methods, OTCCLIP significantly improves CLIP's zero-shot and linear probing performance trained on poisoned datasets.

cs.CV↗

arXiv2025

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data

The efficacy of deep learning models is profoundly influenced by the quality of their training data. Given the considerations of data diversity, data scale, and annotation expenses, model trainers frequently resort to sourcing and acquiring datasets from online repositories. Although economically pragmatic, this strategy exposes the models to substantial security vulnerabilities. Untrusted entities can clandestinely embed triggers within the dataset, facilitating the hijacking of the trained model on the poisoned dataset through backdoor attacks, which constitutes a grave security concern. Despite the proliferation of countermeasure research, their inherent limitations constrain their effectiveness in practical applications. These include the requirement for substantial quantities of clean samples, inconsistent defense performance across varying attack scenarios, and inadequate resilience against adaptive attacks, among others. Therefore, in this paper, we endeavor to address the challenges of backdoor attack countermeasures in real-world scenarios, thereby fortifying the security of training paradigm under the data-collection manner. Concretely, we first explore the inherent relationship between the potential perturbations and the backdoor trigger, and demonstrate the key observation that the poisoned samples perform more robustness to perturbation than the clean ones through the theoretical analysis and experiments. Then, based on our key explorations, we propose a robust and clean-data-free backdoor defense framework, namely Mellivora Capensis (\texttt{MeCa}), which enables the model trainer to train a clean model on the poisoned dataset.

cs.CR↗

arXiv2025

Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE

Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration, however, also introduces a new and critical attack surface. Attackers can exploit these components by injecting malicious instructions into untrusted external sources, effectively hijacking the Agent to perform harmful operations beyond the user's intention or awareness. This emerging threat has quickly attracted research attention, leading to various proposed attack vectors, such as hijacking Model Context Protocol (MCP) Servers to access private data. However, most existing approaches lack stealth and persistence, limiting their practical impact. We propose the Cuckoo Attack, a novel attack that achieves stealthy and persistent command execution by embedding malicious payloads into configuration files. These files, commonly used in AI-IDEs, execute system commands during routine operations, without displaying execution details to the user. Once configured, such files are rarely revisited unless an obvious runtime error occurs, creating a blind spot for attackers to exploit. We formalize our attack paradigm into two stages, including initial infection and persistence. Based on these stages, we analyze the practicality of the attack execution process and identify the relevant exploitation techniques. Furthermore, we analyze the impact of Cuckoo Attack, which can not only invade the developer's local computer but also achieve supply chain attacks through the spread of configuration files. We contribute seven actionable checkpoints for vendors to evaluate their product security. The critical need for these checks is demonstrated by our end-to-end Proof of Concept, which validated the proposed attack across nine mainstream Agent and AI-IDE pairs.

cs.CR↗

arXiv2025

Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes

The rapid advancement of voice deepfake technologies has raised serious concerns about user audio privacy, as attackers increasingly exploit publicly available voice data to generate convincing fake audio for malicious purposes such as identity theft, financial fraud, and misinformation campaigns. While existing defense methods offer partial protection, they face critical limitations, including weak adaptability to unseen user data, poor scalability to long audio, rigid reliance on white-box knowledge, and high computational and temporal costs during the encryption process. To address these challenges and defend against personalized voice deepfake threats, we propose Enkidu, a novel user-oriented privacy-preserving framework that leverages universal frequential perturbations generated through black-box knowledge and few-shot training on a small amount of user data. These highly malleable frequency-domain noise patches enable real-time, lightweight protection with strong generalization across variable-length audio and robust resistance to voice deepfake attacks, all while preserving perceptual quality and speech intelligibility. Notably, Enkidu achieves over 50 to 200 times processing memory efficiency (as low as 0.004 gigabytes) and 3 to 7000 times runtime efficiency (real-time coefficient as low as 0.004) compared to six state-of-the-art countermeasures. Extensive experiments across six mainstream text-to-speech models and five cutting-edge automated speaker verification models demonstrate the effectiveness, transferability, and practicality of Enkidu in defending against both vanilla and adaptive voice deepfake attacks. Our code is currently available.

cs.SD↗

arXiv2025

FreeTalk:A plug-and-play and black-box defense against speech synthesis attacks

Recently, speech assistant and speech verification have been used in many fields, which brings much benefit and convenience for us. However, when we enjoy these speech applications, our speech may be collected by attackers for speech synthesis. For example, an attacker generates some inappropriate political opinions with the characteristic of the victim's voice by obtaining a piece of the victim's speech, which will greatly influence the victim's reputation. Specifically, with the appearance of some zero-shot voice conversion methods, the cost of speech synthesis attacks has been further reduced, which also brings greater challenges to user voice security and privacy. Some researchers have proposed the corresponding privacy-preserving methods. However, the existing approaches have some non-negligible drawbacks: low transferability and robustness, high computational overhead. These deficiencies seriously limit the existing method deployed in practical scenarios. Therefore, in this paper, we propose a lightweight, robust, plug-and-play privacy preservation method against speech synthesis attacks in a black-box setting. Our method generates and adds a frequency-domain perturbation to the original speech to achieve privacy protection and high speech quality. Then, we present a data augmentation strategy and noise smoothing mechanism to improve the robustness of the proposed method. Besides, to reduce the user's defense overhead, we also propose a novel identity-wise protection mechanism. It can generate a universal perturbation for one speaker and support privacy preservation for speech of any length. Finally, we conduct extensive experiments on 5 speech synthesis models, 5 speech verification models, 1 speech recognition model, and 2 datasets. The experimental results demonstrate that our method has satisfying privacy-preserving performance, high speech quality, and utility.

cs.CR↗

arXiv2025

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models

The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous datasets, including unauthorized personal identities, artistic creations, and harmful materials, which can lead to uncontrolled production and distribution of such content. To address this, we propose VideoEraser, a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts, even when explicitly prompted with those concepts. Designed as a plug-and-play module, VideoEraser can seamlessly integrate with representative T2V diffusion models via a two-stage process: Selective Prompt Embedding Adjustment (SPEA) and Adversarial-Resilient Noise Guidance (ARNG). We conduct extensive evaluations across four tasks, including object erasure, artistic style erasure, celebrity erasure, and explicit content erasure. Experimental results show that VideoEraser consistently outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability. Notably, VideoEraser achieves state-of-the-art performance in suppressing undesirable content during T2V generation, reducing it by 46% on average across four tasks compared to baselines.

cs.CV↗

arXiv2025

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced prompting strategies or auxiliary detection models. While these methods have demonstrated some effectiveness, they fundamentally rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors. As a result, agents still retain unrestricted access to tool invocations, leaving them vulnerable to stronger attack vectors that can bypass the security guardrails of the model. To prevent malicious tool invocations at the source, we propose a novel defensive task execution paradigm, called IPIGuard, which models the agents' task execution process as a traversal over a planned Tool Dependency Graph (TDG). By explicitly decoupling action planning from interaction with external data, IPIGuard significantly reduces unintended tool invocations triggered by injected instructions, thereby enhancing robustness against IPI attacks. Experiments on the AgentDojo benchmark show that IPIGuard achieves a superior balance between effectiveness and robustness, paving the way for the development of safer agentic systems in dynamic environments.

cs.CR↗

arXiv2025

Towards Scalable and Interpretable Mobile App Risk Analysis via Large Language Models

Mobile application marketplaces are responsible for vetting apps to identify and mitigate security risks. Current vetting processes are labor-intensive, relying on manual analysis by security professionals aided by semi-automated tools. To address this inefficiency, we propose Mars, a system that leverages Large Language Models (LLMs) for automated risk identification and profiling. Mars is designed to concurrently analyze multiple applications across diverse risk categories with minimal human intervention. To enhance analytical precision and operational efficiency, Mars leverages a pre-constructed risk identification tree to extract relevant indicators from high-dimensional application features. This initial step filters the data, reducing the input volume for the LLM and mitigating the potential for model hallucination induced by irrelevant features. The extracted indicators are then subjected to LLM analysis for final risk determination. Furthermore, Mars automatically generates a comprehensive evidence chain for each assessment, documenting the analytical process to provide transparent justification. These chains are designed to facilitate subsequent manual review and to inform enforcement decisions, such as application delisting. The performance of Mars was evaluated on a real-world dataset from a partner Android marketplace. The results demonstrate that Mars attained an F1-score of 0.838 in risk identification and an F1-score of 0.934 in evidence retrieval. To assess its practical applicability, a user study involving 20 expert analysts was conducted, which indicated that Mars yielded a substantial efficiency gain, ranging from 60% to 90%, over conventional manual analysis.

cs.CR↗

arXiv2025

An Inversion-based Measure of Memorization for Diffusion Models

The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are susceptible to training data memorization, raising significant concerns regarding copyright infringement and privacy invasion. This study delves into a rigorous analysis of memorization in diffusion models. We introduce InvMM, an inversion-based measure of memorization, which is based on inverting a sensitive latent noise distribution accounting for the replication of an image. For accurate estimation of the measure, we propose an adaptive algorithm that balances the normality and sensitivity of the noise distribution. Comprehensive experiments across four datasets, conducted on both unconditional and text-guided diffusion models, demonstrate that InvMM provides a reliable and complete quantification of memorization. Notably, InvMM is commensurable between samples, reveals the true extent of memorization from an adversarial standpoint and implies how memorization differs from membership. In practice, it serves as an auditing tool for developers to reliably assess the risk of memorization, thereby contributing to the enhancement of trustworthiness and privacy-preserving capabilities of diffusion models.

cs.CR↗

arXiv2025

PRSA: Prompt Stealing Attacks against Real-World Prompt Services

Recently, large language models (LLMs) have garnered widespread attention for their exceptional capabilities. Prompts are central to the functionality and performance of LLMs, making them highly valuable assets. The increasing reliance on high-quality prompts has driven significant growth in prompt services. However, this growth also expands the potential for prompt leakage, increasing the risk that attackers could replicate original functionalities, create competing products, and severely infringe on developers' intellectual property. Despite these risks, prompt leakage in real-world prompt services remains underexplored. In this paper, we present PRSA, a practical attack framework designed for prompt stealing. PRSA infers the detailed intent of prompts through very limited input-output analysis and can successfully generate stolen prompts that replicate the original functionality. Extensive evaluations demonstrate PRSA's effectiveness across two main types of real-world prompt services. Specifically, compared to previous works, it improves the attack success rate from 17.8% to 46.1% in prompt marketplaces and from 39% to 52% in LLM application stores, respectively. Notably, in the attack on "Math", one of the most popular educational applications in OpenAI's GPT Store with over 1 million conversations, PRSA uncovered a hidden Easter egg that had not been revealed previously. Besides, our analysis reveals that higher mutual information between a prompt and its output correlates with an increased risk of leakage. This insight guides the design and evaluation of two potential defenses against the security threats posed by PRSA. We have reported these findings to the prompt service vendors, including PromptBase and OpenAI, and actively collaborate with them to implement defensive measures.

cs.CR↗

arXiv2025

VModA: An Effective Framework for Adaptive NSFW Image Moderation

Not Safe/Suitable for Work (NSFW) content is rampant on social networks and poses serious harm to citizens, especially minors. Current detection methods mainly rely on deep learning-based image recognition and classification. However, NSFW images are now presented in increasingly sophisticated ways, often using image details and complex semantics to obscure their true nature or attract more views. Although still understandable to humans, these images often evade existing detection methods, posing a significant threat. Further complicating the issue, varying regulations across platforms and regions create additional challenges for effective moderation, leading to detection bias and reduced accuracy. To address this, we propose VModA, a general and effective framework that adapts to diverse moderation rules and handles complex, semantically rich NSFW content across categories. Experimental results show that VModA significantly outperforms existing methods, achieving up to a 54.3% accuracy improvement across NSFW types, including those with complex semantics. Further experiments demonstrate that our method exhibits strong adaptability across categories, scenarios, and base VLMs. We also identified inconsistent and controversial label samples in public NSFW benchmark datasets, re-annotated them, and submitted corrections to the original maintainers. Two datasets have confirmed the updates so far. Additionally, we evaluate VModA in real-world scenarios to demonstrate its practical effectiveness.

cs.CV↗

arXiv2025

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations manifesting in excessive reliance on training data, poor stealth, and instability, which hinder their effectiveness in real-world applications. Therefore, this paper introduces ShadowPrint, a versatile backdoor attack that targets feature embeddings within neural networks to achieve high ASRs and stealthiness. Unlike traditional approaches, ShadowPrint reduces reliance on training data access and operates effectively with exceedingly low poison rates (as low as 0.01%). It leverages a clustering-based optimization strategy to align feature embeddings, ensuring robust performance across diverse scenarios while maintaining stability and stealth. Extensive evaluations demonstrate that ShadowPrint achieves superior ASR (up to 100%), steady CA (with decay no more than 1% in most cases), and low DDR (averaging below 5%) across both clean-label and dirty-label settings, and with poison rates ranging from as low as 0.01% to 0.05%, setting a new standard for backdoor attack capabilities and emphasizing the need for advanced defense strategies focused on feature space manipulations.

cs.CR↗