CyberSec Research

The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing backdoor-based dataset ownership verification methods suffer from inherent limitations: poison-label watermarks are easily detectable due to label inconsistencies, while clean-label watermarks face high technical complexity and failure on high-resolution images. Moreover, both approaches employ static watermark patterns that are vulnerable to detection and removal. To address these issues, this paper proposes a sample-specific clean-label backdoor watermarking (i.e., SSCL-BW). By training a U-Net-based watermarked sample generator, this method generates unique watermarks for each sample, fundamentally overcoming the vulnerability of static watermark patterns. The core innovation lies in designing a composite loss function with three components: target sample loss ensures watermark effectiveness, non-target sample loss guarantees trigger reliability, and perceptual similarity loss maintains visual imperceptibility. During ownership verification, black-box testing is employed to check whether suspicious models exhibit predefined backdoor behaviors. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method and its robustness against potential watermark removal attacks.

AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions creates a critical vulnerability: instruction injection. Malicious instructions, embedded in otherwise benign content like emails, can hijack the agent to perform unauthorized actions. We present AgentSentry, a lightweight runtime task-centric access control framework that enforces dynamic, task-scoped permissions. Instead of granting broad, persistent permissions, AgentSentry dynamically generates and enforces minimal, temporary policies aligned with the user's specific task (e.g., register for an app), revoking them upon completion. We demonstrate that AgentSentry successfully prevents an instruction injection attack, where an agent is tricked into forwarding private emails, while allowing the legitimate task to complete. Our approach highlights the urgent need for intent-aligned security models to safely govern the next generation of autonomous agents.

Super apps are the cornerstones of modern digital life, embedding financial transactions into nearly every aspect of daily routine. The prevailing security paradigm for these platforms is overwhelmingly focused on pre-transaction authentication, preventing unauthorized payments before they occur. We argue that a critical vulnerability vector has been largely overlooked: the fragility of post-transaction audit trails. We investigate the ease with which a user can permanently erase their transaction history from an app's interface, thereby concealing unauthorized or sensitive activities from the account owner. To quantify this threat, we conducted an empirical study with 6 volunteers who performed a cross-evaluation on six super apps. Our findings are alarming: all six applications studied allow users to delete transaction records, yet a staggering five out of six (83+\%) fail to protect these records with strong authentication. Only one app in our study required biometric verification for deletion. This study provides the first concrete evidence of this near-ubiquitous vulnerability, demonstrating a critical gap in the current mobile security landscape and underscoring the urgent need for a paradigm shift towards ensuring post-transaction audit integrity.

Edge computing alleviates the computation burden of data-driven control in cyber-physical systems (CPSs) by offloading complex processing to edge servers. However, the increasing sophistication of cyberattacks underscores the need for security measures that go beyond conventional IT protections and address the unique vulnerabilities of CPSs. This study proposes a confidential data-driven gain-tuning framework using homomorphic encryption, such as ElGamal and CKKS encryption schemes, to enhance cybersecurity in gain-tuning processes outsourced to external servers. The idea for realizing confidential FRIT is to replace the matrix inversion operation with a vector summation form, allowing homomorphic operations to be applied. Numerical examples under 128-bit security confirm performance comparable to conventional methods while providing guidelines for selecting suitable encryption schemes for secure CPS.

This paper presents a comprehensive empirical analysis of security vulnerabilities in AI-generated code across public GitHub repositories. We collected and analyzed 7,703 files explicitly attributed to four major AI tools: ChatGPT (91.52\%), GitHub Copilot (7.50\%), Amazon CodeWhisperer (0.52\%), and Tabnine (0.46\%). Using CodeQL static analysis, we identified 4,241 Common Weakness Enumeration (CWE) instances across 77 distinct vulnerability types. Our findings reveal that while 87.9\% of AI-generated code does not contain identifiable CWE-mapped vulnerabilities, significant patterns emerge regarding language-specific vulnerabilities and tool performance. Python consistently exhibited higher vulnerability rates (16.18\%-18.50\%) compared to JavaScript (8.66\%-8.99\%) and TypeScript (2.50\%-7.14\%) across all tools. We observed notable differences in security performance, with GitHub Copilot achieving better security density for Python (1,739 LOC per CWE) and TypeScript, while ChatGPT performed better for JavaScript. Additionally, we discovered widespread use of AI tools for documentation generation (39\% of collected files), an understudied application with implications for software maintainability. These findings extend previous work with a significantly larger dataset and provide valuable insights for developing language-specific and context-aware security practices for the responsible integration of AI-generated code into software development workflows.

Local Differential Privacy (LDP) is a widely adopted privacy-protection model in the Internet of Things (IoT) due to its lightweight, decentralized, and scalable nature. However, it is vulnerable to poisoning attacks, and existing defenses either incur prohibitive resource overheads or rely on domain-specific prior knowledge, limiting their practical deployment. To address these limitations, we propose PEEL, a Poisoning-Exposing Encoding theoretical framework for LDP, which departs from resource- or prior-dependent countermeasures and instead leverages the inherent structural consistency of LDP-perturbed data. As a non-intrusive post-processing module, PEEL amplifies stealthy poisoning effects by re-encoding LDP-perturbed data via sparsification, normalization, and low-rank projection, thereby revealing both output and rule poisoning attacks through structural inconsistencies in the reconstructed space. Theoretical analysis proves that PEEL, integrated with LDP, retains unbiasedness and statistical accuracy, while being robust to expose both output and rule poisoning attacks. Moreover, evaluation results show that LDP-integrated PEEL not only outperforms four state-of-the-art defenses in terms of poisoning exposure accuracy but also significantly reduces client-side computational costs, making it highly suitable for large-scale IoT deployments.

Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the audio modality also brings new and unique vulnerability vectors. Previous studies have proposed jailbreak attacks that specifically target ALMs, revealing that defenses directly transferred from traditional audio adversarial attacks or text-based Large Language Model (LLM) jailbreaks are largely ineffective against these ALM-specific threats. To address this issue, we propose ALMGuard, the first defense framework tailored to ALMs. Based on the assumption that safety-aligned shortcuts naturally exist in ALMs, we design a method to identify universal Shortcut Activation Perturbations (SAPs) that serve as triggers that activate the safety shortcuts to safeguard ALMs at inference time. To better sift out effective triggers while preserving the model's utility on benign tasks, we further propose Mel-Gradient Sparse Mask (M-GSM), which restricts perturbations to Mel-frequency bins that are sensitive to jailbreaks but insensitive to speech understanding. Both theoretical analyses and empirical results demonstrate the robustness of our method against both seen and unseen attacks. Overall, \MethodName reduces the average success rate of advanced ALM-specific jailbreak attacks to 4.6% across four models, while maintaining comparable utility on benign benchmarks, establishing it as the new state of the art. Our code and data are available at https://github.com/WeifeiJin/ALMGuard.

The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring their safe deployment. We present SIRAJ: a generic red-teaming framework for arbitrary black-box LLM agents. We employ a dynamic two-step process that starts with an agent definition and generates diverse seed test cases that cover various risk outcomes, tool-use trajectories, and risk sources. Then, it iteratively constructs and refines model-based adversarial attacks based on the execution trajectories of former attempts. To optimize the red-teaming cost, we present a model distillation approach that leverages structured forms of a teacher model's reasoning to train smaller models that are equally effective. Across diverse evaluation agent settings, our seed test case generation approach yields 2 -- 2.5x boost to the coverage of risk outcomes and tool-calling trajectories. Our distilled 8B red-teamer model improves attack success rate by 100%, surpassing the 671B Deepseek-R1 model. Our ablations and analyses validate the effectiveness of the iterative framework, structured reasoning, and the generalization of our red-teamer models.

Modern vehicles remain vulnerable to unauthorized use and theft despite traditional security measures including immobilizers and keyless entry systems. Criminals exploit vulnerabilities in Controller Area Network (CAN) bus systems to bypass authentication mechanisms, while social media trends have expanded auto theft to include recreational joyriding by underage drivers. Driver authentication via CAN bus data offers a promising additional layer of defense-in-depth protection, but existing open-access driver fingerprinting datasets suffer from critical limitations including reliance on decoded diagnostic data rather than raw CAN traffic, artificial fixed-route experimental designs, insufficient sampling rates, and lack of demographic information. This paper provides a comprehensive review of existing open-access driver fingerprinting datasets, analyzing their strengths and limitations to guide practitioners in dataset selection. We introduce the Kidmose CANid Dataset (KCID), which addresses these fundamental shortcomings by providing raw CAN bus data from 16 drivers across four vehicles, including essential demographic information and both daily driving and controlled fixed-route data. Beyond dataset contributions, we present a driver authentication anti-theft framework and implement a proof-of-concept prototype on a single-board computer. Through live road trials with an unaltered passenger vehicle, we demonstrate the practical feasibility of CAN bus-based driver authentication anti-theft systems. Finally, we explore diverse applications of KCID beyond driver authentication, including driver profiling for insurance and safety assessments, mechanical anomaly detection, young driver monitoring, and impaired driving detection. This work provides researchers with both the data and methodological foundation necessary to develop robust, deployable driver authentication systems...

In the rapidly expanding landscape of Large Language Model (LLM) applications, real-time output streaming has become the dominant interaction paradigm. While this enhances user experience, recent research reveals that it exposes a non-trivial attack surface through network side-channels. Adversaries can exploit patterns in encrypted traffic to infer sensitive information and reconstruct private conversations. In response, LLM providers and third-party services are deploying defenses such as traffic padding and obfuscation to mitigate these vulnerabilities. This paper starts by presenting a systematic analysis of contemporary side-channel defenses in mainstream LLM applications, with a focus on services from vendors like OpenAI and DeepSeek. We identify and examine seven representative deployment scenarios, each incorporating active/passive mitigation techniques. Despite these enhanced security measures, our investigation uncovers significant residual information that remains vulnerable to leakage within the network traffic. Building on this discovery, we introduce NetEcho, a novel, LLM-based framework that comprehensively unleashes the network side-channel risks of today's LLM applications. NetEcho is designed to recover entire conversations -- including both user prompts and LLM responses -- directly from encrypted network traffic. It features a deliberate design that ensures high-fidelity text recovery, transferability across different deployment scenarios, and moderate operational cost. In our evaluations on medical and legal applications built upon leading models like DeepSeek-v3 and GPT-4o, NetEcho can recover avg $\sim$70\% information of each conversation, demonstrating a critical limitation in current defense mechanisms. We conclude by discussing the implications of our findings and proposing future directions for augmenting network traffic security.

Increasing complexity and connectivity of modern vehicles have heightened their vulnerability to cyberattacks. This paper addresses security challenges associated with the Unified Diagnostic Services (UDS) protocol, a critical communication framework for vehicle diagnostics in the automotive industry. We present security monitoring strategies for the UDS protocol that leverage in-vehicle logging and remote analysis through a Vehicle Security Operations Center (VSOC). Our approach involves specifying security event logging requirements, contextual data collection, and the development of detection strategies aimed at identifying UDS attack scenarios. By applying these strategies to a comprehensive taxonomy of UDS attack techniques, we demonstrate that our detection methods cover a wide range of potential attack vectors. Furthermore, we assess the adequacy of current AUTOSAR standardized security events in supporting UDS attack detection, identifying gaps in the current standard. This work enhances the understanding of vehicle security monitoring and provides an example for developing robust cybersecurity measures in automotive communication protocols.

To date, traffic obfuscation techniques have been widely adopted to protect network data privacy and security by obscuring the true patterns of traffic. Nevertheless, as the pre-trained models emerge, especially transformer-based classifiers, existing traffic obfuscation methods become increasingly vulnerable, as witnessed by current studies reporting the traffic classification accuracy up to 99\% or higher. To counter such high-performance transformer-based classification models, we in this paper propose a novel and effective \underline{adv}ersarial \underline{traffic}-generating approach (AdvTraffic\footnote{The code and data are available at: http://xxx}). Our approach has two key innovations: (i) a pre-padding strategy is proposed to modify packets, which effectively overcomes the limitations of existing research against transformer-based models for network traffic classification; and (ii) a reinforcement learning model is employed to optimize network traffic perturbations, aiming to maximize adversarial effectiveness against transformer-based classification models. To the best of our knowledge, this is the first attempt to apply adversarial perturbation techniques to defend against transformer-based traffic classifiers. Furthermore, our method can be easily deployed into practical network environments. Finally, multi-faceted experiments are conducted across several real-world datasets, and the experimental results demonstrate that our proposed method can effectively undermine transformer-based classifiers, significantly reducing classification accuracy from 99\% to as low as 25.68\%.

Vision Transformers (ViTs) have emerged as powerful architectures in medical image analysis, excelling in tasks such as disease detection, segmentation, and classification. However, their reliance on large, attention-driven models makes them vulnerable to hardware-level attacks. In this paper, we propose a novel threat model referred to as Med-Hammer that combines the Rowhammer hardware fault injection with neural Trojan attacks to compromise the integrity of ViT-based medical imaging systems. Specifically, we demonstrate how malicious bit flips induced via Rowhammer can trigger implanted neural Trojans, leading to targeted misclassification or suppression of critical diagnoses (e.g., tumors or lesions) in medical scans. Through extensive experiments on benchmark medical imaging datasets such as ISIC, Brain Tumor, and MedMNIST, we show that such attacks can remain stealthy while achieving high attack success rates about 82.51% and 92.56% in MobileViT and SwinTransformer, respectively. We further investigate how architectural properties, such as model sparsity, attention weight distribution, and the number of features of the layer, impact attack effectiveness. Our findings highlight a critical and underexplored intersection between hardware-level faults and deep learning security in healthcare applications, underscoring the urgent need for robust defenses spanning both model architectures and underlying hardware platforms.

Software supply chains, while providing immense economic and software development value, are only as strong as their weakest link. Over the past several years, there has been an exponential increase in cyberattacks specifically targeting vulnerable links in critical software supply chains. These attacks disrupt the day-to-day functioning and threaten the security of nearly everyone on the internet, from billion-dollar companies and government agencies to hobbyist open-source developers. The ever-evolving threat of software supply chain attacks has garnered interest from both the software industry and US government in improving software supply chain security. On Thursday, March 6th, 2025, four researchers from the NSF-backed Secure Software Supply Chain Center (S3C2) conducted a Secure Software Supply Chain Summit with a diverse set of 18 practitioners from 17 organizations. The goals of the Summit were: (1) to enable sharing between participants from different industries regarding practical experiences and challenges with software supply chain security; (2) to help form new collaborations; and (3) to learn about the challenges facing participants to inform our future research directions. The summit consisted of discussions of six topics relevant to the government agencies represented, including software bill of materials (SBOMs); compliance; malicious commits; build infrastructure; culture; and large language models (LLMs) and security. For each topic of discussion, we presented a list of questions to participants to spark conversation. In this report, we provide a summary of the summit. The open questions and challenges that remained after each topic are listed at the end of each topic's section, and the initial discussion questions for each topic are provided in the appendix.

Quantum networks rely on both quantum and classical channels for coordinated operation. Current architectures employ entanglement distribution and key exchange over quantum channels but often assume that classical communication is sufficiently secure. In practice, classical channels protected by traditional cryptography remain vulnerable to quantum adversaries, since large-scale quantum computers could break widely used public-key schemes and reduce the effective security of symmetric cryptography. This perspective presents a quantum-resistant network architecture that secures classical communication with post-quantum cryptographic techniques while supporting entanglement-based communication over quantum channels. Beyond cryptographic protection, the framework incorporates continuous monitoring of both quantum and classical layers, together with orchestration across heterogeneous infrastructures, to ensure end-to-end security. Collectively, these mechanisms provide a pathway toward scalable, robust, and secure quantum networks that remain dependable against both classical and quantum-era threats.

Binarized Neural Networks (BNNs) deployed on memristive crossbar arrays provide energy-efficient solutions for edge computing but are susceptible to physical attacks due to memristor nonvolatility. Recently, Rajendran et al. (IEEE Embedded Systems Letter 2025) proposed a Physical Unclonable Function (PUF)-based scheme to secure BNNs against theft attacks. Specifically, the weight and bias matrices of the BNN layers were secured by swapping columns based on device's PUF key bits. In this paper, we demonstrate that this scheme to secure BNNs is vulnerable to PUF-key recovery attack. As a consequence of our attack, we recover the secret weight and bias matrices of the BNN. Our approach is motivated by differential cryptanalysis and reconstructs the PUF key bit-by-bit by observing the change in model accuracy, and eventually recovering the BNN model parameters. Evaluated on a BNN trained on the MNIST dataset, our attack could recover 85% of the PUF key, and recover the BNN model up to 93% classification accuracy compared to the original model's 96% accuracy. Our attack is very efficient and it takes a couple of minutes to recovery the PUF key and the model parameters.

As the core of the Internet infrastructure, the TCP/IP protocol stack undertakes the task of network data transmission. However, due to the complexity of the protocol and the uncertainty of cross-layer interaction, there are often inconsistencies between the implementation of the protocol stack code and the RFC standard. This inconsistency may not only lead to differences in protocol functions but also cause serious security vulnerabilities. At present, with the continuous expansion of protocol stack functions and the rapid iteration of RFC documents, it is increasingly important to detect and fix these inconsistencies. With the rise of large language models, researchers have begun to explore how to extract protocol specifications from RFC documents through these models, including protocol stack modeling, state machine extraction, text ambiguity analysis, and other related content. However, existing methods rely on predefined patterns or rule-based approaches that fail to generalize across different protocol specifications. Automated and scalable detection of these inconsistencies remains a significant challenge. In this study, we propose an automated analysis framework based on LLM and differential models. By modeling the iterative relationship of the protocol and based on the iterative update relationship of the RFC standard, we perform incremental code function analysis on different versions of kernel code implementations to automatically perform code detection and vulnerability analysis. We conduct extensive evaluations to validate the effectiveness of our framework, demonstrating its effectiveness in identifying potential vulnerabilities caused by RFC code inconsistencies.

Though playing an essential role in smart home systems, smart speakers are vulnerable to voice spoofing attacks. Passive liveness detection, which utilizes only the collected audio rather than the deployed sensors to distinguish between live-human and replayed voices, has drawn increasing attention. However, it faces the challenge of performance degradation under the different environmental factors as well as the strict requirement of the fixed user gestures. In this study, we propose a novel liveness feature, array fingerprint, which utilizes the microphone array inherently adopted by the smart speaker to determine the identity of collected audios. Our theoretical analysis demonstrates that by leveraging the circular layout of microphones, compared with existing schemes, array fingerprint achieves a more robust performance under the environmental change and user's movement. Then, to leverage such a fingerprint, we propose ARRAYID, a lightweight passive detection scheme, and elaborate a series of features working together with array fingerprint. Our evaluation on the dataset containing 32,780 audio samples and 14 spoofing devices shows that ARRAYID achieves an accuracy of 99.84%, which is superior to existing passive liveness detection schemes.