Muhammad Zeeshan Baig

This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel vulnerability class that exploits persistent memory and execution pathways in Large Language Models (LLMs). Unlike surface-level injections, LPCI operations embed malicious logic within vector stores, retrieval systems, and tool outputs, allowing payloads to remain dormant and execute contextually upon later activation. We formalize the LPCI attack through a six-stage lifecycle (reconnaissance, injection, trigger execution, persistence, evasion, and trace tampering). The feasibility and severity of LPCI are demonstrated through a large-scale empirical evaluation of over 1,700 adversarial trials across five major LLM platforms, revealing a cross-platform attack success rate of 43\%. Targeted demonstrations on production systems further confirm critical vulnerabilities in memory retention and logic mediation. To mitigate these vulnerabilities, we further propose the Qorvex Security AI Framework (QSAF), a defense-in-depth architecture that integrates runtime memory validation, cryptographic tool attestation, and context-aware filtering. The implementation of QSAF in our tests reduced the LPCI attack success rate from 43\% to 5.3\%. Our findings necessitate a paradigm shift from static input-output filtering toward runtime enforcement of logic-layer integrity to secure next-generation AI systems.

This paper presents a Unified Security Architecture that fortifies the Agentic Web through a Zero-Trust IAM framework. This architecture is built on a foundation of rich, verifiable agent identities using Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs), with discovery managed by a protocol-agnostic Agent Name Service (ANS). Security is operationalized through a multi-layered Trust Fabric which introduces significant innovations, including Trust-Adaptive Runtime Environments (TARE), Causal Chain Auditing, and Dynamic Identity with Behavioral Attestation. By explicitly linking the LPCI threat to these enhanced architectural countermeasures within a formal security model, we propose a comprehensive and forward-looking blueprint for a secure, resilient, and trustworthy agentic ecosystem. Our formal analysis demonstrates that the proposed architecture provides provable security guarantees against LPCI attacks with bounded probability of success.

We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. These systemic weaknesses lead to silent agent drift, logic collapse, and persistent hallucinations over time. To address this class of failures, we introduce the Qorvex Security AI Framework for Behavioral & Cognitive Resilience (QSAF Domain 10), a lifecycle-aware defense framework defined by a six-stage cognitive degradation lifecycle. The framework includes seven runtime controls (QSAF-BC-001 to BC-007) that monitor agent subsystems in real time and trigger proactive mitigation through fallback routing, starvation detection, and memory integrity enforcement. Drawing from cognitive neuroscience, we map agentic architectures to human analogs, enabling early detection of fatigue, starvation, and role collapse. By introducing a formal lifecycle and real-time mitigation controls, this work establishes Cognitive Degradation as a critical new class of AI system vulnerability and proposes the first cross-platform defense model for resilient agentic behavior.

This paper aims to provide a general review of the fundamental ideas, varieties, methods, and experimental research of the most advanced frequency selective surfaces available today. Frequency-selective surfaces are periodic structures engineered to work as spatial filters in interaction with electromagnetic (EM) waves with different frequencies, polarization, and incident angles in a desired and controlled way. They are usually made of periodic elements with dimensions less than the operational wavelength. The primary issue examined is the need for more efficient, compact, and adaptable electromagnetic filtering solutions. The research method involved a comprehensive review of recent advancements in FSS design, focusing on structural diversity, miniaturization, multiband operations, and the integration of active components for tunability and reconfigurability. Key findings include the development of highly selective miniaturized FSSs, innovative applications on flexible and textile substrates, and the exploration of FSSs for liquid and strain sensing. The conclusions emphasize the significant potential of FSS technology to enhance wireless communication, environmental monitoring, and defense applications. This study provides valuable insights into the design and application of FSSs, aiming to guide future research and development in this dynamic field.

Naturally, humans use multiple modalities to convey information. The modalities are processed both sequentially and in parallel for communication in the human brain, this changes when humans interact with computers. Empowering computers with the capability to process input multimodally is a major domain of investigation in Human-Computer Interaction (HCI). The advancement in technology (powerful mobile devices, advanced sensors, new ways of output, etc.) has opened up new gateways for researchers to design systems that allow multimodal interaction. It is a matter of time when the multimodal inputs will overtake the traditional ways of interactions. The paper provides an introduction to the domain of multimodal systems, explains a brief history, describes advantages of multimodal systems over unimodal systems, and discusses various modalities. The input modeling, fusion, and data collection were discussed. Finally, the challenges in the multimodal systems research were listed. The analysis of the literature showed that multimodal interface systems improve the task completion rate and reduce the errors compared to unimodal systems. The commonly used inputs for multimodal interaction are speech and gestures. In the case of multimodal inputs, late integration of input modalities is preferred by researchers because it allows easy update of modalities and corresponding vocabularies.

Modelling 3D objects in CAD software requires special skills which require a novice user to undergo a series of training exercises to obtain. To minimize the training time for a novice user, the user-dependent factors must be studied. we have presented a comparative analysis of novice/expert information flow patterns. We have used Normalized Transfer Entropy (NTE) and Electroencephalogram (EEG) to investigate the differences. The experiment was divided into three cognitive states i.e., rest, drawing, and manipulation. We applied classification algorithms on NTE matrices and graph theory measures to see the effectiveness of NTE. The results revealed that the experts show approximately the same cognitive activation in drawing and manipulation states, whereas for novices the brain activation is more in manipulation state than drawing state. The hemisphere- and lobe-wise analysis showed that expert users have developed an ability to control the information flow in various brain regions. On the other hand, novice users have shown a continuous increase in information flow activity in almost all regions when doing drawing and manipulation tasks. A classification accuracy of more than 90% was achieved with a simple K-nearest neighbors (k-NN) to classify novice and expert users. The results showed that the proposed technique can be used to develop adaptive 3D modelling systems.