Papers

In todays security landscape, every user wants to access large amounts of data with confidentiality and authorization. To maintain confidentiality, various researchers have proposed several techniques. However, to access secure data, researchers use access control lists to grant authentication and provide authorization. The above several steps will increase the server's computation overhead and response time. To cope with these two problems, we proposed multiparty execution on the server. In this paper, we introduce two different approaches. The first approach is encryption, utilizing the Involution Function Based Stream Cipher to encrypt the file data. The second approach is key distribution, using the Shamir secret sharing scheme to divide and distribute the symmetric key to every user. The decryption process required key reconstruction, which used second order Lagrange interpolation to reconstruct the secret keys from the hidden points. The process will reduce the server's computational overhead. The results are evaluated based on the encryption and decryption time, throughput, computational overhead, and security analysis. In the future, the proposed mechanism will be used to share large-scale, secure data within the organization.

Modern hardware systems, driven by demands for high performance and application-specific functionality, have grown increasingly complex, introducing large surfaces for bugs and security-critical vulnerabilities. Fuzzing has emerged as a scalable solution for discovering such flaws. Yet, existing hardware fuzzers suffer from limited semantic awareness, inefficient test refinement, and high computational overhead due to reliance on slow device simulation. In this paper, we present GoldenFuzz, a novel two-stage hardware fuzzing framework that partially decouples test case refinement from coverage and vulnerability exploration. GoldenFuzz leverages a fast, ISA-compliant Golden Reference Model (GRM) as a “digital twin” of the Device Under Test (DUT). It fuzzes the GRM first, enabling rapid, low-cost test case refinement, accelerating deep architectural exploration and vulnerability discovery on DUT. During the fuzzing pipeline, GoldenFuzz iteratively constructs test cases by concatenating carefully chosen instruction blocks that balance the subtle inter- and intra-instructions quality. A feedback-driven mechanism leveraging insights from both high- and low-coverage samples further enhances GoldenFuzz's capability in hardware state exploration. Our evaluation of three RISC-V processors, RocketChip, BOOM, and CVA6, demonstrates that GoldenFuzz significantly outperforms existing fuzzers in achieving the highest coverage with minimal test case length and computational overhead. GoldenFuzz uncovers all known vulnerabilities and discovers five new ones, four of which are classified as highly severe with CVSS v3 severity scores exceeding seven out of ten. It also identifies two previously unknown vulnerabilities in the commercial BA51-H core extension.

We revisit the task of releasing marginal queries under differential privacy with additive (correlated) Gaussian noise. We first give a construction for answering arbitrary workloads of weighted marginal queries, over arbitrary domains. Our technique is based on releasing queries in the Fourier basis with independent noise with carefully calibrated variances, and reconstructing the marginal query answers using the inverse Fourier transform. We show that our algorithm, which is a factorization mechanism, is exactly optimal among all factorization mechanisms, both for minimizing the sum of weighted noise variances, and for minimizing the maximum noise variance. Unlike algorithms based on optimizing over all factorization mechanisms via semidefinite programming, our mechanism runs in time polynomial in the dataset and the output size. This construction recovers results of Xiao et al. [Neurips 2023] with a simpler algorithm and optimality proof, and a better running time. We then extend our approach to a generalization of marginals which we refer to as product queries. We show that our algorithm is still exactly optimal for this more general class of queries. Finally, we show how to embed extended marginal queries, which allow using a threshold predicate on numerical attributes, into product queries. We show that our mechanism is almost optimal among all factorization mechanisms for extended marginals, in the sense that it achieves the optimal (maximum or average) noise variance up to lower order terms.

The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain vulnerable to adversarial attacks that introduce carefully crafted feature-level perturbations to evade detection while preserving malicious functionality. In this paper, we present LAMLAD, a novel adversarial attack framework that exploits the generative and reasoning capabilities of large language models (LLMs) to bypass ML-based Android malware classifiers. LAMLAD employs a dual-agent architecture composed of an LLM manipulator, which generates realistic and functionality-preserving feature perturbations, and an LLM analyzer, which guides the perturbation process toward successful evasion. To improve efficiency and contextual awareness, LAMLAD integrates retrieval-augmented generation (RAG) into the LLM pipeline. Focusing on Drebin-style feature representations, LAMLAD enables stealthy and high-confidence attacks against widely deployed Android malware detection systems. We evaluate LAMLAD against three representative ML-based Android malware detectors and compare its performance with two state-of-the-art adversarial attack methods. Experimental results demonstrate that LAMLAD achieves an attack success rate (ASR) of up to 97%, requiring on average only three attempts per adversarial sample, highlighting its effectiveness, efficiency, and adaptability in practical adversarial settings. Furthermore, we propose an adversarial training-based defense strategy that reduces the ASR by more than 30% on average, significantly enhancing model robustness against LAMLAD-style attacks.

This systematic literature review surveys technical defenses against software-based cheating in online multiplayer games. Categorizing existing approach-es into server-side detection, client-side anti-tamper, kernel-level anti-cheat drivers, and hardware-assisted TEEs. Each category is evaluated in terms of detection effectiveness, perfor-mance overhead, privacy im-pact, and scalability. The analy-sis highlights key trade-offs, particularly between the high visibility of kernel-level solutions and their privacy and stability risks, versus the low intrusive-ness but limited insight of server-side methods. Overall, the re-view emphasizes the ongoing arms race with cheaters and the need for robust, adversary-resistant anti-cheat designs.

Smart home IoT systems rely on authentication mechanisms to ensure that only authorized entities can control devices and access sensitive functionality. In practice, these mechanisms must balance security with usability, often favoring persistent connectivity and minimal user interaction. This paper presents an empirical analysis of authentication enforcement in deployed smart home IoT devices, focusing on how authentication state is established, reused, and validated during normal operation and under routine network conditions. A set of widely deployed consumer devices, including smart plugs, lighting devices, cameras, and a hub based ecosystem, was evaluated in a controlled residential environment using passive network measurement and controlled interaction through official mobile applications. Authentication behavior was examined during initial pairing, over extended periods of operation, after common network changes, and under replay attempts from a different local network host. The results show that authentication state established during pairing is consistently reused across control actions, persists for extended periods without explicit expiration, and remains valid after network events such as reconnection, address reassignment, and router reboot. Replay experiments demonstrate that previously observed authentication artifacts can often be reused to issue control commands from another host on the same local network with high success rates. These behaviors were observed across multiple device categories and ecosystems. The findings indicate that current smart home IoT authentication mechanisms rely on long lived trust relationships with limited binding to session freshness, network context, or controller identity.

Chat-based cybercrime has emerged as a pervasive threat, with attackers leveraging real-time messaging platforms to conduct scams that rely on trust-building, deception, and psychological manipulation. Traditional defense mechanisms, which operate on static rules or shallow content filters, struggle to identify these conversational threats, especially when attackers use multimedia obfuscation and context-aware dialogue. In this work, we ask a provocative question inspired by the classic Imitation Game: Can machines convincingly pose as human victims to turn deception against cybercriminals? We present LURE (LLM-based User Response Engagement), the first system to deploy Large Language Models (LLMs) as active agents, not as passive classifiers, embedded within adversarial chat environments. LURE combines automated discovery, adversarial interaction, and OCR-based analysis of image-embedded payment data. Applied to the setting of illicit video chat scams on Telegram, our system engaged 53 actors across 98 groups. In over 56 percent of interactions, the LLM maintained multi-round conversations without being noticed as a bot, effectively "winning" the imitation game. Our findings reveal key behavioral patterns in scam operations, such as payment flows, upselling strategies, and platform migration tactics.

In this work we present a publicly verifiable quantum money protocol which assumes close to no quantum computational capabilities. We rely on one-time memories which in turn can be built from quantum conjugate coding and hardware-based assumptions. Specifically, our scheme allows for a limited number of verifications and also allows for quantum tokens for digital signatures. Double spending is prevented by the no-cloning principle of conjugate coding states. An implementation of the concepts presented in this work can be found at https://github.com/neverlocal/otm_billz.

My main worry, and the core of my research, is that our cybersecurity ecosystem is slowly but surely aging and getting old and that aging is becoming an operational risk. This is happening not only because of growing complexity, but more importantly because of accumulation of controls and measures whose effectiveness are uncertain. I introduce a new term for this aging phenomenon: cyber senescence. I will begin my lecture with a short historical overview in which I sketch a development over time that led to this worry for the future of cybersecurity. It is this worry that determined my research agenda and its central theme of the role of uncertainty in cybersecurity. My worry is that waste is accumulating in cyberspace. This waste consists of a multitude of overlapping controls whose risk reductions are uncertain. Unless we start pruning these control frameworks, this waste accumulation causes aging of cyberspace and could ultimately lead to a system collapse.

LLM-based code agents(e.g., ChatGPT Codex) are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are believed to provide improved robustness against obfuscated malicious code, we find that their reasoning chains and semantic abstraction processes exhibit exploitable systematic weaknesses.This allows attackers to covertly embed malicious logic, bypass code review, and propagate backdoored components throughout real-world software supply chains.To investigate this issue, we present CoTDeceptor, the first adversarial code obfuscation framework targeting CoT-enhanced LLM detectors. CoTDeceptor autonomously constructs evolving, hard-to-reverse multi-stage obfuscation strategy chains that effectively disrupt CoT-driven detection logic.We obtained malicious code provided by security enterprise, experimental results demonstrate that CoTDeceptor achieves stable and transferable evasion performance against state-of-the-art LLMs and vulnerability detection agents. CoTDeceptor bypasses 14 out of 15 vulnerability categories, compared to only 2 bypassed by prior methods. Our findings highlight potential risks in real-world software supply chains and underscore the need for more robust and interpretable LLM-powered security analysis systems.

Lateral movement is a tactic that adversaries employ most frequently in enterprise IT environments to traverse between assets. In operational technology (OT) environments, however, few methods exist for lateral movement between domain-specific devices, particularly programmable logic controllers (PLCs). Existing techniques often rely on complex chains of vulnerabilities, which are noisy and can be patched. This paper describes the first PLC-centric lateral movement technique that relies exclusively on the native functionality of the victim environment. This OT-specific form of `living off the land' is herein distinguished as `living off the plant' (LOTP). The described technique also facilitates escape from IP networks onto legacy serial networks via dual-homed PLCs. Furthermore, this technique is covert, leveraging common network communication functions that are challenging to detect. This serves as a reminder of the risks posed by LOTP techniques within OT, highlighting the need for a fundamental reconsideration of traditional OT defensive practices.

In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to practical deployment. In this paper, we focus on optimizing a representative class of attacks that search for the optimal ray direction yielding the minimum $\ell_2$-norm perturbation required to move a benign image into the adversarial region. Inspired by Nesterov's Accelerated Gradient (NAG), we propose a momentum-based algorithm, ARS-OPT, which proactively estimates the gradient with respect to a future ray direction inferred from accumulated momentum. We provide a theoretical analysis of its convergence behavior, showing that ARS-OPT enables more accurate directional updates and achieves faster, more stable optimization. To further accelerate convergence, we incorporate surrogate-model priors into ARS-OPT's gradient estimation, resulting in PARS-OPT with enhanced performance. The superiority of our approach is supported by theoretical guarantees under standard assumptions. Extensive experiments on ImageNet and CIFAR-10 demonstrate that our method surpasses 13 state-of-the-art approaches in query efficiency.

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini, GPT-5-Mini, Gemini-2.5-Flash, Llama-3.1, and Qwen-2.5, using Blooms Taxonomy as a framework. We assess six cognitive dimensions: remembering, understanding, applying, analyzing, evaluating, and creating. Our methodology integrates diverse datasets, including curated multiple-choice questions, vulnerable code snippets (SALLM), course assessments from an Introduction to Software Security course, real-world case studies (XBOW), and project-based creation tasks from a Secure Software Engineering course. Results show that while LLMs perform well on lower-level cognitive tasks such as recalling facts and identifying known vulnerabilities, their performance degrades significantly on higher-order tasks that require reasoning, architectural evaluation, and secure system creation. Beyond reporting aggregate accuracy, we introduce a software security knowledge boundary that identifies the highest cognitive level at which a model consistently maintains reliable performance. In addition, we identify 51 recurring misconception patterns exhibited by LLMs across Blooms levels.

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications. However, this accessibility extends to malicious actors who may exploit these powerful tools to generate harmful software. Existing jailbreaking research primarily focuses on general attack scenarios against LLMs, with limited exploration of malicious code generation as a jailbreak target. To address this gap, we propose SPELL, a comprehensive testing framework specifically designed to evaluate the weakness of security alignment in malicious code generation. Our framework employs a time-division selection strategy that systematically constructs jailbreaking prompts by intelligently combining sentences from a prior knowledge dataset, balancing exploration of novel attack patterns with exploitation of successful techniques. Extensive evaluation across three advanced code models (GPT-4.1, Claude-3.5, and Qwen2.5-Coder) demonstrates SPELL's effectiveness, achieving attack success rates of 83.75%, 19.38%, and 68.12% respectively across eight malicious code categories. The generated prompts successfully produce malicious code in real-world AI development tools such as Cursor, with outputs confirmed as malicious by state-of-the-art detection systems at rates exceeding 73%. These findings reveal significant security gaps in current LLM implementations and provide valuable insights for improving AI safety alignment in code generation applications.

As large language models (LLMs) see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-generated code is crucial. Notably, prior work showed that LLMs are prone to generating code with security vulnerabilities, highlighting that security is often overlooked. These insights were enabled by specialized benchmarks crafted by security experts through significant manual effort. However, benchmarks (i) inevitably end up contaminating training data, (ii) must extend to new tasks to provide a more complete picture, and (iii) must increase in difficulty to challenge more capable LLMs. In this work, we address these challenges and present AutoBaxBuilder, an automated pipeline that generates code security benchmarking tasks from scratch. It leverages the code-understanding capabilities of LLMs combined with robust reliability checks to construct functional tests and end-to-end security-probing exploits. The quality of the pipeline is quantitatively confirmed by aligning its predictions with an expert-written baseline and qualitatively validated through manual soundness verification. We use AutoBaxBuilder to construct a new benchmark and release it to the public as AutoBaxBench, together with a thorough evaluation on contemporary LLMs. AutoBaxBuilder generates new tasks in under 2 hours, for less than USD 4. Including a manual verification, this reduces the required human effort for benchmark construction by a factor of 12.

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities that malicious users can systematically leverage to circumvent safety mechanisms. We empirically evaluate multiple state-of-the-art LLMs, including ChatGPT, Claude, Gemini, and DeepSeek. Our analysis demonstrates the circumvention of reliable safety mechanisms through emotional framing, progressive revelation, and academic justification techniques. Notably, reasoning-enabled configurations amplified rather than mitigated the effectiveness of exploitation, increasing factual precision while failing to interrogate the underlying intent. The exception was Claude Opus 4.1, which prioritized intent detection over information provision in some use cases. This pattern reveals that current architectural designs create systematic vulnerabilities. These limitations require paradigmatic shifts toward contextual understanding and intent recognition as core safety capabilities rather than post-hoc protective mechanisms.

Healthcare AI needs large, diverse datasets, yet strict privacy and governance constraints prevent raw data sharing across institutions. Federated learning (FL) mitigates this by training where data reside and exchanging only model updates, but practical deployments still face two core risks: (1) privacy leakage via gradients or updates (membership inference, gradient inversion) and (2) trust in the aggregator, a single point of failure that can drop, alter, or inject contributions undetected. We present zkFL-Health, an architecture that combines FL with zero-knowledge proofs (ZKPs) and Trusted Execution Environments (TEEs) to deliver privacy-preserving, verifiably correct collaborative training for medical AI. Clients locally train and commit their updates; the aggregator operates within a TEE to compute the global update and produces a succinct ZK proof (via Halo2/Nova) that it used exactly the committed inputs and the correct aggregation rule, without revealing any client update to the host. Verifier nodes validate the proof and record cryptographic commitments on-chain, providing an immutable audit trail and removing the need to trust any single party. We outline system and threat models tailored to healthcare, the zkFL-Health protocol, security/privacy guarantees, and a performance evaluation plan spanning accuracy, privacy risk, latency, and cost. This framework enables multi-institutional medical AI with strong confidentiality, integrity, and auditability, key properties for clinical adoption and regulatory compliance.

Anonymity is a fundamental cryptographic primitive that hides the identities of both senders and receivers during message transmission over a network. Classical protocols cannot provide information-theoretic security for such task, and existing quantum approaches typically depend on classical subroutines and multiple private channels, thereby weakening their security in fully adversarial settings. In this work, we introduce the first fully quantum protocol for anonymous communication in realistic quantum networks with a device-independent security proof.

Mixture-of-Experts (MoE) architectures have advanced the scaling of Large Language Models (LLMs) by activating only a sparse subset of parameters per input, enabling state-of-the-art performance with reduced computational cost. As these models are increasingly deployed in critical domains, understanding and strengthening their alignment mechanisms is essential to prevent harmful outputs. However, existing LLM safety research has focused almost exclusively on dense architectures, leaving the unique safety properties of MoEs largely unexamined. The modular, sparsely-activated design of MoEs suggests that safety mechanisms may operate differently than in dense models, raising questions about their robustness. In this paper, we present GateBreaker, the first training-free, lightweight, and architecture-agnostic attack framework that compromises the safety alignment of modern MoE LLMs at inference time. GateBreaker operates in three stages: (i) gate-level profiling, which identifies safety experts disproportionately routed on harmful inputs, (ii) expert-level localization, which localizes the safety structure within safety experts, and (iii) targeted safety removal, which disables the identified safety structure to compromise the safety alignment. Our study shows that MoE safety concentrates within a small subset of neurons coordinated by sparse routing. Selective disabling of these neurons, approximately 3% of neurons in the targeted expert layers, significantly increases the averaged attack success rate (ASR) from 7.4% to 64.9% against the eight latest aligned MoE LLMs with limited utility degradation. These safety neurons transfer across models within the same family, raising ASR from 17.9% to 67.7% with one-shot transfer attack. Furthermore, GateBreaker generalizes to five MoE vision language models (VLMs) with 60.9% ASR on unsafe image inputs.

The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human activity understanding. However, the reliability of these systems is critically undermined by their vulnerability to prompt injection attacks, where attackers deliberately input deceptive instructions into LLMs. Traditional defenses, based on static filters and rigid rules, are insufficient to address the semantic complexity of these new attacks. We argue that a paradigm shift is needed – from passive filtering to active protection and autonomous reasoning. We introduce AegisAgent, an autonomous agent system designed to ensure the security of LLM-driven HAR systems. Instead of merely blocking threats, AegisAgent functions as a cognitive guardian. It autonomously perceives potential semantic inconsistencies, reasons about the user's true intent by consulting a dynamic memory of past interactions, and acts by generating and executing a multi-step verification and repair plan. We implement AegisAgent as a lightweight, full-stack prototype and conduct a systematic evaluation on 15 common attacks with five state-of-the-art LLM-based HAR systems on three public datasets. Results show it reduces attack success rate by 30% on average while incurring only 78.6 ms of latency overhead on a GPU workstation. Our work makes the first step towards building secure and trustworthy LLM-driven HAR systems.

Autonomous Vehicles (AVs) refer to systems capable of perceiving their states and moving without human intervention. Among the factors required for autonomous decision-making in mobility, positional awareness of the vehicle itself is the most critical. Accordingly, extensive research has been conducted on defense mechanisms against GPS spoofing attacks, which threaten AVs by disrupting position recognition. Among these, detection methods based on internal IMU sensors are regarded as some of the most effective. In this paper, we propose a spoofing attack system designed to neutralize IMU sensor-based detection. First, we present an attack modeling approach for bypassing such detection. Then, based on EKF sensor fusion, we experimentally analyze both the impact of GPS spoofing values on the internal target system and how our proposed methodology reduces anomaly detection within the target system. To this end, this paper proposes an attack model that performs GPS spoofing by stealing internal dynamic state information using an external IMU sensor, and the experimental results demonstrate that attack values can be injected without being detected.

Function call graphs (FCGs) have emerged as a powerful abstraction for malware detection, capturing the behavioral structure of applications beyond surface-level signatures. Their utility in traditional program analysis has been well established, enabling effective classification and analysis of malicious software. In the mobile domain, especially in the Android ecosystem, FCG-based malware classification is particularly critical due to the platform's widespread adoption and the complex, component-based structure of Android apps. However, progress in this direction is hindered by the lack of large-scale, high-quality Android-specific FCG datasets. Existing datasets are often outdated, dominated by small or redundant graphs resulting from app repackaging, and fail to reflect the diversity of real-world malware. These limitations lead to overfitting and unreliable evaluation of graph-based classification methods. To address this gap, we introduce Better Call Graphs (BCG), a comprehensive dataset of large and unique FCGs extracted from recent Android application packages (APKs). BCG includes both benign and malicious samples spanning various families and types, along with graph-level features for each APK. Through extensive experiments using baseline classifiers, we demonstrate the necessity and value of BCG compared to existing datasets. BCG is publicly available at https://erdemub.github.io/BCG-dataset.

Dynamic malware analysis requires executing untrusted binaries inside strongly isolated, rapidly resettable environments. In practice, many detonation workflows remain tied to heavyweight hypervisors or dedicated bare-metal labs, limiting portability and automation. This challenge has intensified with the adoption of ARM64 developer hardware (e.g., Apple Silicon), where common open-source sandbox recipes and pre-built environments frequently assume x86_64 hosts and do not translate cleanly across architectures. This paper presents pokiSEC, a lightweight, ephemeral malware detonation sandbox that packages the full virtualization and access stack inside a Docker container. pokiSEC integrates QEMU with hardware acceleration (KVM when available) and exposes a browser-based workflow that supports bring-your-own Windows disk images. The key contribution is a Universal Entrypoint that performs runtime host-architecture detection and selects validated hypervisor configurations (machine types, acceleration modes, and device profiles), enabling a single container image and codebase to launch Windows guests on both ARM64 and x86_64 hosts. We validate pokiSEC on Apple Silicon (ARM64) and Ubuntu (AMD64), demonstrating interactive performance suitable for analyst workflows and consistent teardown semantics via ephemeral container lifecycles.

Autonomous vehicles rely on LiDAR based perception to support safety critical control functions such as adaptive cruise control and automatic emergency braking. While previous research has shown that LiDAR perception can be manipulated through object based spoofing and injection attacks, the impact of such attacks on vehicle safety controllers is still not well understood. This paper presents a systematic failure analysis of longitudinal safety controllers under object based LiDAR attacks in highway driving scenarios. The study focuses on realistic cut in and car following situations in which adversarial objects introduce persistent perception errors without directly modifying vehicle control software. A high fidelity simulation framework integrating LiDAR perception, object tracking, and closed loop vehicle control is used to evaluate how false and displaced object detections propagate through the perception planning and control pipeline. The results demonstrate that even short duration LiDAR induced object hallucinations can trigger unsafe braking, delayed responses to real hazards, and unstable control behavior. In cut in scenarios, a clear increase in unsafe deceleration events and time to collision violations is observed when compared to benign conditions, despite identical controller parameters. The analysis further shows that controller failures are more strongly influenced by the temporal consistency of spoofed objects than by spatial inaccuracies alone. These findings reveal a critical gap between perception robustness and control level safety guarantees in autonomous driving systems. By explicitly characterizing safety controller failure modes under adversarial perception, this work provides practical insights for the design of attack aware safety mechanisms and more resilient control strategies for LiDAR dependent autonomous vehicles.

Video semantic communication, praised for its transmission efficiency, still faces critical challenges related to privacy leakage. Traditional security techniques like steganography and encryption are challenging to apply since they are not inherently robust against semantic-level transformations and abstractions. Moreover, the temporal continuity of video enables framewise statistical modeling over extended periods, which increases the risk of exposing distributional anomalies and reconstructing hidden content. To address these challenges, we propose SemCovert, a deep semantic-level hiding framework for secure and covert video transmission. SemCovert introduces a pair of co-designed models, namely the semantic hiding model and the secret semantic extractor, which are seamlessly integrated into the semantic communication pipeline. This design enables authorized receivers to reliably recover hidden information, while keeping it imperceptible to regular users. To further improve resistance to analysis, we introduce a randomized semantic hiding strategy, which breaks the determinism of embedding and introduces unpredictable distribution patterns. The experimental results demonstrate that SemCovert effectively mitigates potential eavesdropping and detection risks while reliably concealing secret videos during transmission. Meanwhile, video quality suffers only minor degradation, preserving transmission fidelity. These results confirm SemCovert's effectiveness in enabling secure and covert transmission without compromising semantic communication performance.

Modern networks generate vast, heterogeneous traffic that must be continuously analyzed for security and performance. Traditional network traffic analysis systems, whether rule-based or machine learning-driven, often suffer from high false positives and lack interpretability, limiting analyst trust. In this paper, we present ReGAIN, a multi-stage framework that combines traffic summarization, retrieval-augmented generation (RAG), and Large Language Model (LLM) reasoning for transparent and accurate network traffic analysis. ReGAIN creates natural-language summaries from network traffic, embeds them into a multi-collection vector database, and utilizes a hierarchical retrieval pipeline to ground LLM responses with evidence citations. The pipeline features metadata-based filtering, MMR sampling, a two-stage cross-encoder reranking mechanism, and an abstention mechanism to reduce hallucinations and ensure grounded reasoning. Evaluated on ICMP ping flood and TCP SYN flood traces from the real-world traffic dataset, it demonstrates robust performance, achieving accuracy between 95.95% and 98.82% across different attack types and evaluation benchmarks. These results are validated against two complementary sources: dataset ground truth and human expert assessments. ReGAIN also outperforms rule-based, classical ML, and deep learning baselines while providing unique explainability through trustworthy, verifiable responses.

The successful deployment of the Internet of Things (IoT) applications relies heavily on their robust security, and lightweight cryptography is considered an emerging solution in this context. While existing surveys have been examining lightweight cryptographic techniques from the perspective of hardware and software implementations or performance evaluation, there is a significant gap in addressing different security aspects, such as design principles, specific to the IoT environment. This study aims to bridge this gap. This research presents an examination with focusing on the security evaluation of symmetric lightweight ciphers commonly used in IoT systems. The objective of this study is to provide a concise overview of lightweight ciphers with emphasizing on their security challenges which is an essential consideration for real-time and resource-constrained applications.

The rapid proliferation of satellite constellations, particularly in Low Earth Orbit (LEO), has fundamentally altered the global space infrastructure, shifting the risk landscape from purely kinetic collisions to complex cyber-physical threats. While traditional safety frameworks focus on debris mitigation, ground-based adversaries increasingly exploit radio-frequency links, supply chain vulnerabilities, and software update pathways to degrade space assets. This paper presents a comparative analysis of satellite cybersecurity across LEO, Medium Earth Orbit (MEO), and Geostationary Earth Orbit (GEO) regimes. By synthesizing data from 60 publicly documented security incidents with key vulnerability proxies–including Telemetry, Tracking, and Command (TT&C) anomalies, encryption weaknesses, and environmental stressors–we characterize how orbital altitude dictates attack feasibility and impact. Our evaluation reveals distinct threat profiles: GEO systems are predominantly targeted via high-frequency uplink exposure, whereas LEO constellations face unique risks stemming from limited power budgets, hardware constraints, and susceptibility to thermal and radiation-induced faults. We further bridge the gap between security and sustainability, arguing that unmitigated cyber vulnerabilities accelerate hardware obsolescence and debris accumulation, undermining efforts toward carbon-neutral space operations. The results demonstrate that weak encryption and command path irregularities are the most consistent predictors of adversarial success across all orbits.

Security in modern RISC-V processors demands more than functional correctness: It requires resilience to side-channel attacks. This paper evaluates the vulnerability of the side channel of the CVA6 RISC-V core by analyzing software-based AES encryption uses an RTL-level power profiling framework called VeriSide. This work represents that this design's Correlation Power Analysis (CPA) reveals significant leakage, enabling key recovery. These findings underscore the importance of early-stage RTL assessments in shaping future secure RISC-V designs.

"f differential privacy" (fDP) is a recent definition for privacy privacy which can offer improved predictions of "privacy loss". It has been used to analyse specific privacy mechanisms, such as the popular Gaussian mechanism. In this paper we show how fDP's foundation in statistical hypothesis testing implies equivalence to the channel model of Quantitative Information Flow. We demonstrate this equivalence by a Galois connection between two partially ordered sets. This equivalence enables novel general composition theorems for fDP, supporting improved analysis for complex privacy designs.