The Dark Side of LLMs Agent-Based Attacks for Complete Computer Takeover

The rapid adoption of Large Language Model LLM agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. Th...

Never Trust the Manufacturer, Never Trust the Client: a Novel Method for Streaming STL Files for Secure Additive Manufacturing

While additive manufacturing has opened interesting avenues to reimagine manufacturing as a service MaaS platform, transmission of design files from client to manufacturer over networks opens up many cybersecurity challenges. Securing client's intellectual property IP especially from cyber-attack...

Quantum-Resilient Privacy Ledger (QRPL): a Sovereign Digital Currency for the Post-Quantum Era

The emergence of quantum computing presents profound challenges to existing cryptographic infrastructures, whilst the development of central bank digital currencies CBDCs has raised concerns regarding privacy preservation and excessive centralisation in digital payment systems. This paper propose...

FortiWeb SQL Injection / Remote Code Execution

This script attempts to detect if FortiWeb is vulnerable to CVE-2025-25257, a SQL injection vulnerability that can be leveraged for remote code execution...

Microsoft Windows 11 CVE-2025-49744 Checker

This archive contains a PowerShell script to validate whether a Microsoft Windows 11 system is vulnerable to CVE-2025-49744, a critical local privilege escalation vulnerability involving the gdi32.dll and win32kfull.sys system components. It does not actively exploit anything...

When and Where Do Data Poisons Attack Textual Inversion?

Poisoning attacks pose significant challenges to the robustness of diffusion models DMs. In this paper, we systematically analyze when and where poisoning attacks textual inversion TI, a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method fo...

Evaluating Post-Quantum Cryptographic Algorithms on Resource-Constrained Devices

Whitepaper called Evaluating Post-Quantum Cryptographic Algorithms On Resource-Constrained Devices...

MH-FSF: a Unified Framework for Overcoming Benchmarking and Reproducibility Limitations in Feature Selection Evaluation

Feature selection is vital for building effective predictive models, as it reduces dimensionality and emphasizes key features. However, current research often suffers from limited benchmarking and reliance on proprietary datasets. This severely hinders reproducibility and can negatively impact...

ARPaCCino: an Agentic-RAG for Policy As Code Compliance

Policy as Code PaC is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code IaC environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In th...

Breaking a 5-Bit Elliptic Curve Key Using a 133-Qubit Quantum Computer

This experiment breaks a 5-bit elliptic curve cryptographic key using a Shor-style quantum attack. Executed on IBM's 133-qubit ibmtorino with Qiskit Runtime 2.0, a 15-qubit circuit, comprised of 10 logical qubits and 5 ancilla, interferes over an order-32 elliptic curve subgroup to extract the...

Entangled Threats: a Unified Kill Chain Model for Quantum Machine Learning Security

Quantum Machine Learning QML systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoni...

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models

While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards -- ranked platforms for model discovery and evaluation --...

CovertAuth: Joint Covert Communication and Authentication in MmWave Systems

Beam alignment BA is a crucial process in millimeter-wave mmWave communications, enabling precise directional transmission and efficient link establishment. However, due to characteristics like omnidirectional exposure and the broadcast nature of the BA phase, it is particularly vulnerable to...

SSH-Passkeys: Leveraging Web Authentication for Passwordless SSH

We propose a method for using Web Authentication APIs for SSH authentication, enabling passwordless remote server login with passkeys. These are credentials that are managed throughout the key lifecycle by an authenticator on behalf of the user and offer strong security guarantees. Passwords rema...

Characterizing Security and Privacy Teaching Standards for Schools in the United States

Increasingly, students begin learning aspects of security and privacy during their primary and secondary education grades K-12 in the United States. Individual U.S. states and some national organizations publish teaching standards -- guidance that outlines expectations for what students should...

Kernel Live Patch Security Notice LSN-0113-1

Several security issues were fixed in the kernel relating to out of bounds access and use-after-free vulnerabilities...

Favicon Trojans: Executable Steganography Via Ico Alpha Channel Exploitation

This paper presents a novel method of executable steganography using the alpha transparency layer of ICO image files to embed and deliver self-decompressing JavaScript payloads within web browsers. By targeting the least significant bit LSB of non-transparent alpha layer image values, the propose...

GPUHammer: Rowhammer Attacks on GPU Memories Are Practical

Rowhammer is a read disturbance vulnerability in modern DRAM that causes bit-flips, compromising security and reliability. While extensively studied on Intel and AMD CPUs with DDR and LPDDR memories, its impact on GPUs using GDDR memories, critical for emerging machine learning applications,...

EinHops: Einsum Notation for Expressive Homomorphic Operations on RNS-CKKS Tensors

Fully Homomorphic Encryption FHE is an encryption scheme that allows for computation to be performed directly on encrypted data, effectively closing the loop on secure and outsourced computing. Data is encrypted not only during rest and transit, but also during processing. However, FHE provides a...

KeyDroid: a Large-Scale Analysis of Secure Key Storage in Android Apps

Most contemporary mobile devices offer hardware-backed storage for cryptographic keys, user data, and other sensitive credentials. Such hardware protects credentials from extraction by an adversary who has compromised the main operating system, such as a malicious third-party app. Since 2011,...

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this pape...

The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web

The fragmentation of AI agent ecosystems has created urgent demands for interoperability, trust, and economic coordination that current protocols -- including MCP Hou et al., 2025, A2A Habler et al., 2025, ACP Liu et al., 2025, and Cisco's AGP Edwards, 2025 -- cannot address at scale. We present...

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing

Jailbreak attacks reveal critical vulnerabilities in Large Language Models LLMs by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the sophistication required in effectively probing their...

Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm

There is growing interest in giving AI agents access to cryptocurrencies as well as to the smart contracts that transact them. But doing so, this position paper argues, could lead to formidable new vectors of AI harm. To support this argument, we first examine the unique properties of...

Towards Privacy-Preserving and Personalized Smart Homes Via Tailored Small Language Models

Large Language Models LLMs have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home assistants typically transmit user commands, along with user profiles and home...

Microsoft Office Outlook Code Execution

This proof-of-concept exploit demonstrates a code execution vulnerability in Microsoft Outlook. It injects a crafted mail item into Outlook containing a malicious sync path that triggers an action during scanning...

Autonomous AI-Based Cybersecurity Framework for Critical Infrastructure: Real-Time Threat Mitigation

Critical infrastructure systems, including energy grids, healthcare facilities, transportation networks, and water distribution systems, are pivotal to societal stability and economic resilience. However, the increasing interconnectivity of these systems exposes them to various cyber threats,...

TruChain: a Multi-Layer Architecture for Trusted, Verifiable, and Immutable Open Banking Data

Open banking framework enables third party providers to access financial data across banking institutions, leading to unprecedented innovations in the financial sector. However, some open banking standards remain susceptible to severe technological risks, including unverified data sources,...

RADAR: a Radio-Based Analytics for Dynamic Association and Recognition of Pseudonyms in VANETs

This paper presents RADAR, a tracking algorithm for vehicles participating in Cooperative Intelligent Transportation Systems C-ITS that exploits multiple radio signals emitted by a modern vehicle to break privacy-preserving pseudonym schemes deployed in VANETs. This study shows that by combining...

Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking

With the rise of social media, vast amounts of user-uploaded videos e.g., YouTube are utilized as training data for Visual Object Tracking VOT. However, the VOT community has largely overlooked video data-privacy issues, as many private videos have been collected and used for training commercial...

LINE: Public-Key Encryption

We propose a public key encryption cryptosystem based on solutions of linear equation systems with predefinition of input parameters through shared secret computation for factorizable substitutions. The existence of multiple equivalent solutions for an underdetermined system of linear equations...

Quantum Properties Trojans (QuPTs) for Attacking Quantum Neural Networks

Quantum neural networks QNN hold immense potential for the future of quantum machine learning QML. However, QNN security and robustness remain largely unexplored. In this work, we proposed novel Trojan attacks based on the quantum computing properties in a QNN-based binary classifier. Our propose...

Rainbow Artifacts from Electromagnetic Signal Injection Attacks on Image Sensors

Image sensors are integral to a wide range of safety- and security-critical systems, including surveillance infrastructure, autonomous vehicles, and industrial automation. These systems rely on the integrity of visual data to make decisions. In this work, we investigate a novel class of...

WinRAR Directory Traversal

WinRAR suffers from a directory traversal vulnerability that allows an attacker to place files outside the intended extraction directory when a user extracts a specially crafted .rar archive. Versions prior to 7.12 are affected...

Defending against Prompt Injection with a Few DefensiveTokens

When large language model LLM systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker is able to override the initial user task with an arbitrary...

Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries

Differential Privacy DP is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior information, more sophisticated attack goals, and complex...

Hedge Funds on a Swamp: Analyzing Patterns, Vulnerabilities, and Defense Measures in Blockchain Bridges [Experiment, Analysis and Benchmark]

Blockchain bridges have become essential infrastructure for enabling interoperability across different blockchain networks, with more than $24B monthly bridge transaction volume. However, their growing adoption has been accompanied by a disproportionate rise in security breaches, making them the...

Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

May I Have Your Attention? Breaking Fine-Tuning Based Prompt Injection Defenses Using Architecture-Aware Attacks

A popular class of defenses against prompt injection attacks on large language models LLMs relies on fine-tuning the model to separate instructions and data, so that the LLM does not follow instructions that might be present with data. There are several academic systems and production-level...

Phishing Detection in the Gen-AI Era: Quantized LLMs Vs Classical Models

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning ML, Deep Learning DL, and quantized...

libxslt xmlNode.psvi Type Confusion

libxslt suffers from a type confusion vulnerability in xmlNode.psvi between stylesheet and source nodes...

Hybrid LLM-Enhanced Intrusion Detection for Zero-Day Threats in IoT Networks

This paper presents a novel approach to intrusion detection by integrating traditional signature-based methods with the contextual understanding capabilities of the GPT-2 Large Language Model LLM. As cyber threats become increasingly sophisticated, particularly in distributed, heterogeneous, and...

Mitigating Watermark Stealing Attacks in Generative Models Via Multi-Key Watermarking

Watermarking offers a promising solution for GenAI providers to establish the provenance of their generated content. A watermark is a hidden signal embedded in the generated content, whose presence can later be verified using a secret watermarking key. A threat to GenAI providers are \emphwaterma...

Supporting Intel(R) SGX on Multi-Package Platforms

Intelr Software Guard Extensions SGX was originally released on client platforms and later extended to single socket server platforms. As developers have become familiar with the capabilities of the technology, the applicability of this capability in the cloud has been tested. Various Cloud Servi...

A Formal Rebuttal of "The Blockchain Trilemma: a Formal Proof of the Inherent Trade-Offs among Decentralization, Security, and Scalability"

This paper presents a comprehensive refutation of the so-called "blockchain trilemma," a widely cited but formally ungrounded claim asserting an inherent trade-off between decentralisation, security, and scalability in blockchain protocols. Through formal analysis, empirical evidence, and detaile...

Invariant-Based Robust Weights Watermark for Large Language Models

Watermarking technology has gained significant attention due to the increasing importance of intellectual property IP rights, particularly with the growing deployment of large language models LLMs on billions resource-constrained edge devices. To counter the potential threats of IP theft by...

Approximating Euler Totient Function Using Linear Regression on RSA Moduli

The security of the RSA cryptosystem is based on the intractability of computing Euler's totient function phin for large integers n. Although deriving phin deterministically remains computationally infeasible for cryptographically relevant bit lengths, and machine learning presents a promising...

AdeptHEQ-FL: Adaptive Homomorphic Encryption for Federated Learning of Hybrid Classical-Quantum Models with Dynamic Layer Sparing

Federated Learning FL faces inherent challenges in balancing model performance, privacy preservation, and communication efficiency, especially in non-IID decentralized environments. Recent approaches either sacrifice formal privacy guarantees, incur high overheads, or overlook quantum-enhanced...

Disa: Accurate Learning-Based Static Disassembly with Attentions

For reverse engineering related security domains, such as vulnerability detection, malware analysis, and binary hardening, disassembly is crucial yet challenging. The fundamental challenge of disassembly is to identify instruction and function boundaries. Classic approaches rely on file-format...

Automated Attack Testflow Extraction from Cyber Threat Report Using BERT for Contextual Analysis

In the ever-evolving landscape of cybersecurity, the rapid identification and mitigation of Advanced Persistent Threats APTs is crucial. Security practitioners rely on detailed threat reports to understand the tactics, techniques, and procedures TTPs employed by attackers. However, manually...