315 papers
This paper proposes a structured, goal-driven risk assessment framework that utilizes attack trees to contextualize and harmonize LLM-specific threats with conventional cyber attacks, demonstrating its effectiveness through a healthcare case study to enable more precise risk prioritization and secure-by-design practices.
This paper introduces Image-based Prompt Injection (IPI), a black-box attack that embeds adversarial instructions into natural images to hijack Multimodal Large Language Models, demonstrating a 64% success rate in manipulating model outputs while remaining visually imperceptible to humans.
This paper proposes an SEIRV epidemic model with relapse and intervention to analyze malware propagation dynamics, establish stability conditions, identify key influencing parameters, and optimize cost-effective control strategies using a hybrid gradient-based framework calibrated with real-world infection data.
This paper introduces a structure-aware framework for distributed backdoor attacks in federated learning that utilizes novel metrics to quantify how model architectures influence perturbation effectiveness, revealing that structural properties like multi-path feature fusion significantly amplify attack success even under low poisoning ratios.
This paper evaluates the feasibility and limitations of using LLM-driven agents to autonomously audit dark patterns in CCPA data rights request workflows across 456 websites, assessing their ability to navigate interfaces, classify manipulative designs, and identify failure conditions.
This paper proposes a neuro-symbolic multi-agent system that leverages hypernym-hyponym semantic relations to extract information from Cyber Threat Intelligence reports and automatically generate CLIPS-based firewall rules, demonstrating superior performance in threat mitigation compared to baseline approaches.
This paper proposes a calibrated, multi-dimensional quality scoring framework for decentralized LLM inference that decomposes output quality into modular dimensions, demonstrating that selectively removing unreliable metrics and re-weighting them yields a robust signal that matches or exceeds single-evaluator baselines while effectively integrating with Proof of Quality mechanisms to mitigate adversarial attacks.
This paper introduces CAM-LDS, a comprehensive and reproducible dataset of cyber attack manifestations across 81 techniques designed to overcome the scarcity of labeled data, thereby enabling and demonstrating the potential of Large Language Models for automated, semantically rich interpretation of system logs and security alerts without relying on manual domain-specific configurations.
This paper introduces "Bayesian Adversarial Privacy," a new quantitative framework that offers a more contextual and rigorous alternative to differential privacy and statistical disclosure theory by grounding disclosure decisions in a prior viewpoint derived from Bayesian decision theory.
PTOPOFL is a privacy-preserving personalized federated learning framework that replaces gradient sharing with compact persistent homology descriptors to simultaneously mitigate data-reconstruction risks and improve aggregation performance on non-IID data through topology-guided clustering and weighted aggregation.
This paper introduces Adversarially-Aligned Jacobian Regularization (AAJR), a novel trajectory-aligned method that enhances the robustness of agentic AI systems by selectively controlling sensitivity along adversarial directions, thereby achieving superior stability and performance compared to overly conservative global Jacobian constraints.
This paper analyzes a decade-long dataset of 2 million YouTube videos to reveal that while affiliate marketing is widespread, disclosure compliance with FTC guidelines remains critically low, suggesting that platform-standardized features are essential for improving transparency and trust in the influencer economy.
This paper presents a full-stack methodology and experimental implementation of quantum oblivious transfer and quantum tokens on the same hardware used for quantum key distribution, demonstrating the feasibility of transitioning from single-purpose networks to versatile, multi-purpose quantum communication systems.
This paper presents a comprehensive review of Multiparty Quantum Key Agreement (MQKA) by organizing protocols along three axes—network architecture, quantum resources, and security models—to analyze fairness trade-offs, classify existing schemes, and propose a research roadmap for future quantum internet deployments.
This paper proposes a secure, lossless, and efficient multi-party federated XGBoost framework that utilizes secret sharing and distributed optimization to overcome data isolation issues and outperform existing state-of-the-art models in both security and performance.