Papers

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests. When adversarial instructions appear in user queries or externally retrieved content, models may override intended logic. Recent defenses rely on supervised fine-tuning with benign and malicious labels. Although these methods achieve high attack rejection rates, we find that they rely on narrow correlations in defense data rather than harmful intent, leading to systematic rejection of safe inputs. We analyze three recurring shortcut behaviors induced by defense fine-tuning. Position bias arises when benign content placed later in a prompt is rejected at much higher rates; across reasoning benchmarks, suffix-task rejection rises from below 10% to as high as 90%. Token trigger bias occurs when strings common in attack data raise rejection probability even in benign contexts; inserting a single trigger token increases false refusals by up to 50%. Topic generalization bias reflects poor generalization beyond the defense data distribution, with defended models suffering test-time accuracy drops of up to 40%. These findings suggest that current prompt-injection defenses frequently respond to attack-like surface patterns rather than the underlying intent. We introduce controlled diagnostic datasets and a systematic evaluation across two base models and multiple defense pipelines, highlighting limitations of supervised fine-tuning for reliable LLM security.

Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated environments, particularly defenses against malicious clients, remains underexplored. To investigate the security of FedLLM, we conduct a preliminary study to analyze potential attack surfaces and defensive characteristics from the perspective of LoRA updates. We find two key properties of FedLLM: 1) LLMs are vulnerable to attacks from malicious clients in FL, and 2) LoRA updates exhibit distinct behavioral patterns that can be effectively distinguished by lightweight classifiers. Based on these properties, we propose Safe-FedLLM, a probe-based defense framework for FedLLM, which constructs defenses across three levels: Step-Level, Client-Level, and Shadow-Level. The core concept of Safe-FedLLM is to perform probe-based discrimination on each client's local LoRA updates, treating them as high-dimensional behavioral features and using a lightweight classifier to determine whether they are malicious. Extensive experiments demonstrate that Safe-FedLLM effectively improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data. Notably, our method effectively suppresses the impact of malicious data without significantly affecting training speed, and remains effective even under high malicious client ratios.

This paper investigates PASS-enabled downlink covert communication in the presence of distributed surveillance, where multiple wardens perform signal detection and fuse their local binary decisions via majority-voting rule. We consider a dual-waveguide architecture that simultaneously delivers covert information and randomized jamming to hide the transmission footprint, incorporating three representative PASS power-radiation laws-general, proportional, and equal. To characterize the system-level detectability, we derive closed-form expressions for local false-alarm and miss-detection probabilities. By leveraging a probability-generating-function (PGF) and elementary-symmetric-polynomial (ESP) framework, combined with a breakpoint-based partition of the threshold domain, we obtain explicit closed-form characterizations of the system-level detection error probability (DEP) under non-i.i.d. majority-voting fusion. Building on this analytical framework, we formulate a robust optimization problem to maximize the average covert rate subject to covertness constraint. To solve the resulting nonconvex design, we develop an MM-BCD-SCA algorithm that produces tractable alternating updates for power/radiation variables and PA positions via convex surrogates and inner approximations of the DEP value function. Numerical results validate the theoretical analysis and demonstrate the impact of cooperative monitoring and PASS radiation laws on the covertness-rate tradeoff.

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block inappropriate prompts or erase sensitive concepts from the models. However, all the existing defense methods are not well prepared to handle diverse adversarial prompts. In this work, we introduce MacPrompt, a novel black-box and cross-lingual attack that reveals previously overlooked vulnerabilities in T2I safety mechanisms. Unlike existing attacks that rely on synonym substitution or prompt obfuscation, MacPrompt constructs macaronic adversarial prompts by performing cross-lingual character-level recombination of harmful terms, enabling fine-grained control over both semantics and appearance. By leveraging this design, MacPrompt crafts prompts with high semantic similarity to the original harmful inputs (up to 0.96) while bypassing major safety filters (up to 100%). More critically, it achieves attack success rates as high as 92% for sex-related content and 90% for violence, effectively breaking even state-of-the-art concept removal defenses. These results underscore the pressing need to reassess the robustness of existing T2I safety mechanisms against linguistically diverse and fine-grained adversarial strategies.

Consensus mechanisms are the core of any blockchain system. However, the majority of these mechanisms do not target federated learning directly nor do they aid in the aggregation step. This paper introduces Proof of Reasoning (PoR), a novel consensus mechanism specifically designed for federated learning using blockchain, aimed at preserving data privacy, defending against malicious attacks, and enhancing the validation of participating networks. Unlike generic blockchain consensus mechanisms commonly found in the literature, PoR integrates three distinct processes tailored for federated learning. Firstly, a masked autoencoder (MAE) is trained to generate an encoder that functions as a feature map and obfuscates input data, rendering it resistant to human reconstruction and model inversion attacks. Secondly, a downstream classifier is trained at the edge, receiving input from the trained encoder. The downstream network's weights, a single encoded datapoint, the network's output and the ground truth are then added to a block for federated aggregation. Lastly, this data facilitates the aggregation of all participating networks, enabling more complex and verifiable aggregation methods than previously possible. This three-stage process results in more robust networks with significantly reduced computational complexity, maintaining high accuracy by training only the downstream classifier at the edge. PoR scales to large IoT networks with low latency and storage growth, and adapts to evolving data, regulations, and network conditions.

While virtualization and resource pooling empower cloud networks with structural flexibility and elastic scalability, they inevitably expand the attack surface and challenge cyber resilience. Reinforcement Learning (RL)-based defense strategies have been developed to optimize resource deployment and isolation policies under adversarial conditions, aiming to enhance system resilience by maintaining and restoring network availability. However, existing approaches lack robustness as they require retraining to adapt to dynamic changes in network structure, node scale, attack strategies, and attack intensity. Furthermore, the lack of Human-in-the-Loop (HITL) support limits interpretability and flexibility. To address these limitations, we propose CyberOps-Bots, a hierarchical multi-agent reinforcement learning framework empowered by Large Language Models (LLMs). Inspired by MITRE ATT&CK's Tactics-Techniques model, CyberOps-Bots features a two-layer architecture: (1) An upper-level LLM agent with four modules–ReAct planning, IPDRR-based perception, long-short term memory, and action/tool integration–performs global awareness, human intent recognition, and tactical planning; (2) Lower-level RL agents, developed via heterogeneous separated pre-training, execute atomic defense actions within localized network regions. This synergy preserves LLM adaptability and interpretability while ensuring reliable RL execution. Experiments on real cloud datasets show that, compared to state-of-the-art algorithms, CyberOps-Bots maintains network availability 68.5% higher and achieves a 34.7% jumpstart performance gain when shifting the scenarios without retraining. To our knowledge, this is the first study to establish a robust LLM-RL framework with HITL support for cloud defense.

Technology-facilitated abuse (TFA) is a pervasive form of intimate partner violence (IPV) that leverages digital tools to control, surveil, or harm survivors. While tech clinics are one of the reliable sources of support for TFA survivors, they face limitations due to staffing constraints and logistical barriers. As a result, many survivors turn to online resources for assistance. With the growing accessibility and popularity of large language models (LLMs), and increasing interest from IPV organizations, survivors may begin to consult LLM-based chatbots before seeking help from tech clinics. In this work, we present the first expert-led manual evaluation of four LLMs - two widely used general-purpose non-reasoning models and two domain-specific models designed for IPV contexts - focused on their effectiveness in responding to TFA-related questions. Using real-world questions collected from literature and online forums, we assess the quality of zero-shot single-turn LLM responses generated with a survivor safety-centered prompt on criteria tailored to the TFA domain. Additionally, we conducted a user study to evaluate the perceived actionability of these responses from the perspective of individuals who have experienced TFA. Our findings, grounded in both expert assessment and user feedback, provide insights into the current capabilities and limitations of LLMs in the TFA context and may inform the design, development, and fine-tuning of future models for this domain. We conclude with concrete recommendations to improve LLM performance for survivor support.

Identity Security Posture Management (ISPM) is a core challenge for modern enterprises operating across cloud and SaaS environments. Answering basic ISPM visibility questions, such as understanding identity inventory and configuration hygiene, requires interpreting complex identity data, motivating growing interest in agentic AI systems. Despite this interest, there is currently no standardized way to evaluate how well such systems perform ISPM visibility tasks on real enterprise data. We introduce the Sola Visibility ISPM Benchmark, the first benchmark designed to evaluate agentic AI systems on foundational ISPM visibility tasks using a live, production-grade identity environment spanning AWS, Okta, and Google Workspace. The benchmark focuses on identity inventory and hygiene questions and is accompanied by the Sola AI Agent, a tool-using agent that translates natural-language queries into executable data exploration steps and produces verifiable, evidence-backed answers. Across 77 benchmark questions, the agent achieves strong overall performance, with an expert accuracy of 0.84 and a strict success rate of 0.77. Performance is highest on AWS hygiene tasks, where expert accuracy reaches 0.94, while results on Google Workspace and Okta hygiene tasks are more moderate, yet competitive. Overall, this work provides a practical and reproducible benchmark for evaluating agentic AI systems in identity security and establishes a foundation for future ISPM benchmarks covering more advanced identity analysis and governance tasks.

Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, their robustness under adversarial conditions remains untested, and current evaluations decouple security from functionality, potentially inflating reported gains. We present the first systematic adversarial audit of state-of-the-art secure code generation methods (SVEN, SafeCoder, PromSec). We subject them to realistic prompt perturbations such as paraphrasing, cue inversion, and context manipulation that developers might inadvertently introduce or adversaries deliberately exploit. To enable fair comparison, we evaluate all methods under consistent conditions, jointly assessing security and functionality using multiple analyzers and executable tests. Our findings reveal critical robustness gaps: static analyzers overestimate security by 7 to 21 times, with 37 to 60% of “secure” outputs being non-functional. Under adversarial conditions, true secure-and-functional rates collapse to 3 to 17%. Based on these findings, we propose best practices for building and evaluating robust secure code generation methods. Our code is available.

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model behavior once retrieved. Previous studies have highlighted this risk but often avoid the hardest step: ensuring that malicious content is actually retrieved. In practice, unoptimized IPI is rarely retrieved under natural queries, which leaves its real-world impact unclear. We address this challenge by decomposing the malicious content into a trigger fragment that guarantees retrieval and an attack fragment that encodes arbitrary attack objectives. Based on this idea, we design an efficient and effective black-box attack algorithm that constructs a compact trigger fragment to guarantee retrieval for any attack fragment. Our attack requires only API access to embedding models, is cost-efficient (as little as $0.21 per target user query on OpenAI's embedding models), and achieves near-100% retrieval across 11 benchmarks and 8 embedding models (including both open-source models and proprietary services). Based on this attack, we present the first end-to-end IPI exploits under natural queries and realistic external corpora, spanning both RAG and agentic systems with diverse attack objectives. These results establish IPI as a practical and severe threat: when a user issued a natural query to summarize emails on frequently asked topics, a single poisoned email was sufficient to coerce GPT-4o into exfiltrating SSH keys with over 80% success in a multi-agent workflow. We further evaluate several defenses and find that they are insufficient to prevent the retrieval of malicious text, highlighting retrieval as a critical open vulnerability.

We propose a novel digital signature cryptosystem that exploits the concept of the brute-force problem. To ensure the security of the cryptosystem, we employed several mechanisms: sharing a common secret for factorable permutations, associating permutations with the message being signed, and confirming knowledge of the shared secret using a zero-knowledge proof. We developed a secret-sharing theory based on homomorphic matrix transformations for factorized permutations. The inverse matrix transformation for computing the shared secret is determined by secret parameters, which results in incompletely defined functionality and gives rise to a brute-force cryptanalysis problem. Randomization of session keys using a message hash and random parameters guarantees the uniqueness of each signature, even for identical messages. We employed a zero-knowledge authentication protocol to confirm knowledge of the shared secret, thereby protecting the verifier against unauthorized signature imposition. The LINEture cryptosystem is built on linear matrix algebra and does not rely on a computationally hard problem. High security is achieved through the appropriate selection of matrix transformation dimensions. Matrix computations potentially offer low operational costs for signature generation and verification.

As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that anchors the reasoning capabilities of Large Language Models (LLMs) to the immutable audit trails of blockchain technology. Specifically, we integrate Gemini 2.0 Pro for logic-based vulnerability detection with the Avalanche C-Chain for tamper-evident artifact logging. Unlike fully decentralized solutions that suffer from high latency, Zer0n employs a hybrid architecture: execution remains off-chain for performance, while integrity proofs are finalized on-chain. Our evaluation on a dataset of 500 endpoints reveals that this approach achieves 80% detection accuracy with only a marginal 22.9% overhead, effectively demonstrating that decentralized integrity can coexist with high-speed security workflows.

This paper provides a comprehensive literature review on the belief in false information, including misinformation, disinformation, and fake information. It addresses the increasing societal concern regarding false information, which is fueled by technological progress, especially advancements in artificial intelligence. This review systematically identifies and categorizes factors that influence the belief in false information. The review identifies 24 influence factors grouped into six main categories: demographic factors, personality traits, psychological factors, policy and values, media consumption, and preventive factors. Key findings highlight that lower education levels, high extraversion, low agreeableness, high neuroticism, and low cognitive reflection significantly increase belief in false information. The effectiveness of preventive strategies like labeling false information and promoting reflection about correctness is also discussed. This literature review conceptualizes belief in false information as a human-centered security risk in sociotechnical systems, as it can be exploited to manipulate decisions, undermine trust, and increase susceptibility to social engineering. It aims to inform preventive strategies that strengthen socio-technical security and societal resilience.

AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal data and learning of user preferences. However, centralization creates a trust crisis where users must entrust cloud providers with sensitive digital memory data. We identify a core tension between personalization demands and data sovereignty: centralized memory systems enable efficient cross-agent collaboration but expose users' sensitive data to cloud provider risks, while private deployments provide security but limit collaboration. To resolve this tension, we aim to achieve local-equivalent security while enabling superior maintenance efficiency and collaborative capabilities. We propose a five-layer architecture abstracting common functional components of AI memory systems: Storage, Extraction, Learning, Retrieval, and Governance. By applying TEE protection to each layer, we establish a trustworthy framework. Based on this, we design MemTrust, a hardware-backed zero-trust architecture that provides cryptographic guarantees across all layers. Our contributions include the five-layer abstraction, "Context from MemTrust" protocol for cross-application sharing, side-channel hardened retrieval with obfuscated access patterns, and comprehensive security analysis. The architecture enables third-party developers to port existing systems with acceptable development costs, achieving system-wide trustworthiness. We believe that AI memory plays a crucial role in enhancing the efficiency and collaboration of agents and AI tools. AI memory will become the foundational infrastructure for AI agents, and MemTrust serves as a universal trusted framework for AI memory systems, with the goal of becoming the infrastructure of memory infrastructure.

The Newton method has been widely adopted to achieve certified unlearning. A critical assumption in existing approaches is that the data requested for unlearning are selected i.i.d.(independent and identically distributed). However,the problem of certified unlearning under non-i.i.d. deletions remains largely unexplored. In practice, unlearning requests are inherently biased, leading to non-i.i.d. deletions and causing distribution shifts between the original and retained datasets. In this paper, we show that certified unlearning with the Newton method becomes inefficient and ineffective under non-i.i.d. unlearning sets. We then propose a better certified unlearning approach by performing a distribution-aware certified unlearning framework based on iterative Newton updates constrained by a trust region. Our method provides a closer approximation to the retrained model and yields a tighter pre-run bound on the gradient residual, thereby ensuring efficient (epsilon, delta)-certified unlearning. To demonstrate its practical effectiveness under distribution shift, we also conduct extensive experiments across multiple evaluation metrics, providing a comprehensive assessment of our approach.

Open-source software (OSS) is a critical component of modern software systems, yet supply chain security remains challenging in practice due to unavailable or obfuscated source code. Consequently, security teams often rely on runtime observations collected from sandboxed executions to investigate suspicious third-party components. We present HeteroGAT-Rank, an industry-oriented runtime behavior mining system that supports analyst-in-the-loop supply chain threat investigation. The system models execution-time behaviors of OSS packages as lightweight heterogeneous graphs and applies attention-based graph learning to rank behavioral patterns that are most relevant for security analysis. Rather than aiming for fully automated detection, HeteroGAT-Rank surfaces actionable runtime signals - such as file, network, and command activities - to guide manual investigation and threat hunting. To operate at ecosystem scale, the system decouples offline behavior mining from online analysis and integrates parallel graph construction for efficient processing across multiple ecosystems. An evaluation on a large-scale OSS execution dataset shows that HeteroGAT-Rank effectively highlights meaningful and interpretable behavioral indicators aligned with real-world vulnerability and attack trends, supporting practical security workflows under realistic operational constraints.

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine unlearning strategies, we argue that these methods mainly aim at removing samples rather than removing samples' influence on the model, thus overlooking the fundamental definition of machine unlearning. In this paper, we first conduct a comprehensive study to evaluate the effectiveness of existing unlearning schemes when the training dataset includes many samples similar to those targeted for unlearning. Specifically, we evaluate: Do existing unlearning methods truly adhere to the original definition of machine unlearning and effectively eliminate all influence of target samples when similar samples are present in the training dataset? Our extensive experiments, conducted on four carefully constructed datasets with thorough analysis, reveal a notable gap between the expected and actual performance of most existing unlearning methods for image and language models, even for the retraining-from-scratch baseline. Additionally, we also explore potential solutions to enhance current unlearning approaches.

Large language models (LLMs) demonstrate remarkable capabilities in natural language understanding and generation. Despite being trained on large-scale, high-quality data, LLMs still fail to outperform traditional static analysis tools in specialized domains like smart contract vulnerability detection. To address this issue, this paper proposes a post-training algorithm based on atomic task decomposition and fusion. This algorithm aims to achieve combinatorial generalization under limited data by decomposing complex reasoning tasks. Specifically, we decompose the reentrancy vulnerability detection task into four linearly independent atomic tasks: identifying external calls, identifying state updates, identifying data dependencies between external calls and state updates, and determining their data flow order. These tasks form the core components of our approach. By training on synthetic datasets, we generate three compiler-verified datasets. We then employ the Slither tool to extract structural information from the control flow graph and data flow graph, which is used to fine-tune the LLM's adapter. Experimental results demonstrate that low-rank normalization fusion with the LoRA adapter improves the LLM's reentrancy vulnerability detection accuracy to 98.2%, surpassing state-of-the-art methods. On 31 real-world contracts, the algorithm achieves a 20% higher recall than traditional analysis tools.

Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learning (FL). Unfortunately, existing MIA defenses, typically applied independently to each client in FL, are ineffective against powerful trajectory-based MIAs that exploit temporal information throughout the training process to infer membership status. In this paper, we investigate a new FL defense scenario driven by heterogeneous privacy needs and privacy-utility trade-offs, where only a subset of clients are defended, as well as a collaborative defense mode where clients cooperate to mitigate membership privacy leakage. To this end, we introduce CoFedMID, a collaborative defense framework against MIAs in FL, which limits local model memorization of training samples and, through a defender coalition, enhances privacy protection and model utility. Specifically, CoFedMID consists of three modules: a class-guided partition module for selective local training samples, a utility-aware compensation module to recycle contributive samples and prevent their overconfidence, and an aggregation-neutral perturbation module that injects noise for cancellation at the coalition level into client updates. Extensive experiments on three datasets show that our defense framework significantly reduces the performance of seven MIAs while incurring only a small utility loss. These results are consistently verified across various defense settings.

The quality of the user experience has become one of the most important aspects in todays world, as it directly influences individuals willingness to continue using or abandon a product or service. In this context, video conferencing applications (VCAs), which experienced widespread adoption following the COVID-19 pandemic, must deliver excellent performance to remain competitive in an increasingly crowded market. Although content providers (CPs) such as Zoom, WhatsApp, Telegram, and Google Meet can assess conversation quality by comparing transmitted and received data. The widespread use of end-to-end encryption in VCAs makes quality-of-experience (QoE) evaluation by internet service providers (ISPs) far more challenging. Since ISPs do not have access to the encrypted content, they must rely on passive measurements of unencrypted traffic characteristics on the data path. In this work, we present a simple yet effective QoE prediction framework based on an almost stock convolutional neural network (CNN) architecture that uses only the packet sizes extracted from the communication between two participants in a video conferencing (VC) call to predict two QoE metrics: BRISQUE and MOS. The proposed framework is simple, easy to implement, and does not require high-end computational resources, yet it provides superior prediction performance, as shown in our experiments on two custom datasets collected from WhatsApp and Zoom, which achieve substantial improvements over previous models for the QoE prediction task.

Modern software package registries like PyPI have become critical infrastructure for software development, but are increasingly exploited by threat actors distributing malicious packages with sophisticated multi-stage attack chains. While Large Language Models (LLMs) offer promising capabilities for automated code analysis, their application to security-critical malware detection faces fundamental challenges, including hallucination and context confusion, which can lead to missed detections or false alarms. We present CHASE (Collaborative Hierarchical Agents for Security Exploration), a high-reliability multi-agent architecture that addresses these limitations through a Plan-and-Execute coordination model, specialized Worker Agents focused on specific analysis aspects, and integration with deterministic security tools for critical operations. Our key insight is that reliability in LLM-based security analysis emerges not from improving individual model capabilities but from architecting systems that compensate for LLM weaknesses while leveraging their semantic understanding strengths. Evaluation on a dataset of 3,000 packages (500 malicious, 2,500 benign) demonstrates that CHASE achieves 98.4% recall with only 0.08% false positive rate, while maintaining a practical median analysis time of 4.5 minutes per package, making it suitable for operational deployment in automated package screening. Furthermore, we conducted a survey with cybersecurity professionals to evaluate the generated analysis reports, identifying their key strengths and areas for improvement. This work provides a blueprint for building reliable AI-powered security tools that can scale with the growing complexity of modern software supply chains. Our project page is available at https://t0d4.github.io/CHASE-AIware25/

Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE) architecture, which has emerged as a promising technique to scale up model capacity with minimal overhead. However, given that the current secure two-party (2-PC) protocols allow the server to homomorphically compute the FFN layer with its plaintext model weight, under the MoE setting, this could reveal which expert is activated to the server, exposing token-level privacy about the client's input. While naively evaluating all the experts before selection could protect privacy, it nullifies MoE sparsity and incurs the heavy computational overhead that sparse MoE seeks to avoid. To address the privacy and efficiency limitations above, we propose a 2-PC privacy-preserving inference framework, \SecMoE. Unifying per-entry circuits in both the MoE layer and piecewise polynomial functions, \SecMoE obliviously selects the extracted parameters from circuits and only computes one encrypted entry, which we refer to as Select-Then-Compute. This makes the model for private inference scale to 63$\times$ larger while only having a 15.2$\times$ increase in end-to-end runtime. Extensive experiments show that, under 5 expert settings, \SecMoE lowers the end-to-end private inference communication by 1.8$\sim$7.1$\times$ and achieves 1.3$\sim$3.8$\times$ speedup compared to the state-of-the-art (SOTA) protocols.

Large Language Models (LLMs) such as Gemma-2B have shown strong performance in various natural language processing tasks. However, general-purpose models often lack the domain expertise required for cybersecurity applications. This work presents a methodology to fine-tune the Gemma-2B model into a domain-specific cybersecurity LLM. We detail the processes of dataset preparation, fine-tuning, and synthetic data generation, along with implications for real-world applications in threat detection, forensic investigation, and attack analysis. Experiments highlight challenges in prompt length distribution during domain-specific fine-tuning. Uneven prompt lengths limit the model's effective use of the context window, constraining local inference to 200-400 tokens despite hardware support for longer sequences. Chain-of-thought styled prompts, paired with quantized weights, yielded the best performance under these constraints. To address context limitations, we employed a hybrid strategy using cloud LLMs for synthetic data generation and local fine-tuning for deployment efficiency. To extend the evaluation, we introduce a Retrieval-Augmented Generation (RAG) pipeline and graph-based reasoning framework. This approach enables structured alignment with MITRE ATT&CK techniques through STIX-based threat intelligence, enhancing recall in multi-hop and long-context scenarios. Graph modules encode entity-neighborhood context and tactic chains, helping mitigate the constraints of short prompt windows. Results demonstrate improved model alignment with tactic, technique, and procedure (TTP) coverage, validating the utility of graph-augmented LLMs in cybersecurity threat intelligence applications.

Phishing with Quick Response (QR) codes is termed as Quishing. The attackers exploit this method to manipulate individuals into revealing their confidential data. Recently, we see the colorful and fancy representations of QR codes, the 2D matrix of QR codes which does not reflect a typical mixture of black-white modules anymore. Instead, they become more tempting as an attack vector for adversaries which can evade the state-of-the-art deep learning visual-based and other prevailing countermeasures. We introduce "ALFA", a safe-by-design approach, to mitigate Quishing and prevent everyone from accessing the post-scan harmful payload of fancy QR codes. Our method first converts a fancy QR code into the replica of binary grid and then identify the erroneous representation of modules in that grid. Following that, we present "FAST" method which can conveniently recover erroneous modules from that binary grid. Afterwards, using this binary grid, our solution extracts the structural features of fancy QR code and predicts its legitimacy using a pre-trained model. The effectiveness of our proposal is demonstrated by the experimental evaluation on a synthetic dataset (containing diverse variations of fancy QR codes) and achieve a FNR of 0.06% only. We also develop the mobile app to test the practical feasibility of our solution and provide a performance comparison of the app with the real-world QR readers. This comparison further highlights the classification reliability and detection accuracy of this solution in real-world environments.

Advanced Persistent Threats (APTs) represent hidden, multi\-stage cyberattacks whose long term persistence and adaptive behavior challenge conventional intrusion detection systems (IDS). Although recent advances in machine learning and probabilistic modeling have improved APT detection performance, most existing approaches remain reactive and alert\-centric, providing limited capability for stage-aware prediction and principled inference under uncertainty, particularly when observations are sparse or incomplete. This paper proposes E\-HiDNet, a unified hybrid deep probabilistic learning framework that integrates convolutional and recurrent neural networks with a Hidden Markov Model (HMM) to allow accurate prediction of the progression of the APT campaign. The deep learning component extracts hierarchical spatio\-temporal representations from correlated alert sequences, while the HMM models latent attack stages and their stochastic transitions, allowing principled inference under uncertainty and partial observability. A modified Viterbi algorithm is introduced to handle incomplete observations, ensuring robust decoding under uncertainty. The framework is evaluated using a synthetically generated yet structurally realistic APT dataset (S\-DAPT\-2026). Simulation results show that E\-HiDNet achieves up to 98.8\-100% accuracy in stage prediction and significantly outperforms standalone HMMs when four or more observations are available, even under reduced training data scenarios. These findings highlight that combining deep semantic feature learning with probabilistic state\-space modeling enhances predictive APT stage performance and situational awareness for proactive APT defense.

Privacy-preserving data processing refers to the methods and models that allow computing and analyzing sensitive data with a guarantee of confidentiality. As cloud computing and applications that rely on data continue to expand, there is an increasing need to protect personal, financial and healthcare information. Conventional centralized data processing methods expose sensitive data to risk of breaches, compelling the need to use decentralized and secure data methods. This paper gives a detailed review of privacy-saving mechanisms in the cloud platform, such as statistical approaches like differential privacy and cryptographic solutions like homomorphic encryption. Federated analytics and federated learning, two distributed learning frameworks, are also discussed. Their principles, applications, benefits, and limitations are reviewed, with roles of use in the fields of healthcare, finance, IoT, and industrial cases. Comparative analyses measure trade-offs in security, efficiency, scalability, and accuracy, and investigations are done of emerging hybrid frameworks to provide better privacy protection. Critical issues, including computational overhead, privacy-utility trade-offs, standardization, adversarial threats, and cloud integration are also addressed. This review examines in detail the recent privacy-protecting approaches in cloud computation and offers scholars and practitioners crucial information on secure and effective solutions to data processing.

Insider threats are a particularly tricky cybersecurity issue, especially in zero-trust architectures (ZTA) where implicit trust is removed. Although the rule of thumb is never trust, always verify, attackers can still use legitimate credentials and impersonate the standard user activity. In response, behavioral analytics with machine learning (ML) can help monitor the user activity continuously and identify the presence of anomalies. This introductory framework makes use of the CERT Insider Threat Dataset for data cleaning, normalization, and class balance using the Synthetic Minority Oversampling Technique (SMOTE). It also employs Principal Component Analysis (PCA) for dimensionality reduction. Several benchmark models, including Support Vector Machine (SVM), Artificial Neural Network (ANN), and Bayesian Network (Bayes Net), were used to develop and evaluate the AdaBoost classifier. Compared to SVM (90.1%), ANN (94.7%), and Bayes Net (94.9), AdaBoost achieved higher performance with a 98.0% ACC, 98.3% PRE, 98.0% REC, and F1-score (F1). The Receiver Operating Characteristic (ROC) study, which provided further confirmation of its strength, yielded an Area Under the Curve (AUC) of 0.98. These results prove the effectiveness and dependability of AdaBoost-based behavioral analytics as a solution to reinforcing continuous insider threat detection in zero-trust settings.

Public blockchains, though renowned for their transparency and immutability, suffer from significant privacy concerns. Network-level analysis and long-term observation of publicly available transactions can often be used to infer user identities. To mitigate this, several blockchain applications rely on relayers, which serve as intermediary nodes between users and smart contracts deployed on the blockchain. However, dependence on a single relayer not only creates a single point of failure but also introduces exploitable vulnerabilities that weaken the system's privacy guarantees. This paper proposes a decentralized relayer architecture that enhances privacy and reliability through game-theoretic incentive design. We model the interaction among relayers as a non-cooperative game and design an incentive mechanism in which probabilistic uploading emerges as a unique mixed Nash equilibrium. Using evolutionary game analysis, we demonstrate the equilibrium's stability against perturbations and coordinated deviations. Through numerical evaluations, we analyze how equilibrium strategies and system behavior evolve with key parameters such as the number of relayers, upload costs, rewards, and penalties. In particular, we show that even with high transaction costs, the system maintains reliability with an outage probability below 0.05 . Furthermore, our results highlight a fundamental trade-off between privacy, reliability, robustness, and cost in decentralized relayer systems.

The detection of advanced persistent threats (APTs) remains a crucial challenge due to their stealthy, multistage nature and the limited availability of realistic, labeled datasets for systematic evaluation. Synthetic dataset generation has emerged as a practical approach for modeling APT campaigns; however, existing methods often rely on computationally expensive alert correlation mechanisms that limit scalability. Motivated by these limitations, this paper presents a near realistic synthetic APT dataset and an efficient alert correlation framework. The proposed approach introduces a machine learning based correlation module that employs K Nearest Neighbors (KNN) clustering with a cosine similarity metric to group semantically related alerts within a temporal context. The dataset emulates multistage APT campaigns across campus and organizational network environments and captures a diverse set of fourteen distinct alert types, exceeding the coverage of commonly used synthetic APT datasets. In addition, explicit APT campaign states and alert to stage mappings are defined to enable flexible integration of new alert types and support stage aware analysis. A comprehensive statistical characterization of the dataset is provided to facilitate reproducibility and support APT stage predictions.

Ransomware is still one of the most serious cybersecurity threats. Victims often pay but fail to regain access to their data, while also facing the danger of losing data privacy. These uncertainties heavily shape the attacker-victim dynamics in decision-making. In this paper, we introduce and analyze zkRansomware. This new ransomware model integrates zero-knowledge proofs to enable verifiable data recovery and uses smart contracts to enforce multi-round payments while mitigating the risk of data disclosure and privacy loss. We show that zkRansomware is technically feasible using existing cryptographic and blockchain tools and, perhaps counterintuitively, can align incentives between the attacker and the victim. Finally, we develop a theoretical decision-making framework for zkRansomware that distinguishes it from known ransomware decision models and discusses its implications for ransomware risk analysis and response decision support.