Can LLMs Hack Enterprise Networks? -- Replicated Computational Results (RCR) Report

This is the Replicated Computational Results RCR Report for the paper "Can LLMs Hack Enterprise Networks?" The paper empirically investigates the efficacy and effectiveness of different LLMs for penetration-testing enterprise networks, i.e., Microsoft Active Directory Assumed-Breach Simulations...

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models

The deployment of Large Reasoning Models LRMs in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought CoT is manipulated to provide a linguistically plausible but logically fallacio...

Exploiting PendingIntent Provenance Confusion to Spoof Android SDK Authentication

A single authentication bypass in a partner SDK grants attackers the identity of every partner in the ecosystem -- and millions of apps use SDKs with exactly this vulnerability. OWASP's 2024 Mobile Top 10 ranks Inadequate Supply Chain Security as the second most critical mobile risk, explicitly...

Extending the Formalism and Theoretical Foundations of Cryptography to AI

Recent progress in Large Language Models LMs has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant autonomy and authority. The security community has been...

Comparison of Credential Management Systems Based on the Standards of IEEE, ETSI, and YD/T 3957-2021

As V2X Vehicle-to-Everything technology becomes increasingly prevalent, the security of V2X networks has garnered growing attention worldwide. In North America, the IEEE 1609 series standards are primarily used, while Europe adopts the ETSI series standards, and China has also established its...

Phishing the Phishers with SpecularNet: Hierarchical Graph Autoencoding for Reference-Free Web Phishing Detection

Phishing remains the most pervasive threat to the Web, enabling large-scale credential theft and financial fraud through deceptive webpages. While recent reference-based and generative-AI-driven phishing detectors achieve strong accuracy, their reliance on external knowledge bases, cloud services...

ClawShield 1.0.0

ClawShield is a security proxy for AI agents. It scans all inbound and outbound messages for prompt injection, PII leaks, and secrets...

SDN-SYN PoW: Intent-Aware Adaptive SDN Defense with PoW against Multi-Domain SYN Floods

The stability of Internet services is persistently challenged by the escalating scale of volumetric TCP SYN floods, as conventional defenses like SYN Cookies fail by exacerbating bandwidth depletion under modern attacks. This paper introduces SDN-SYN PoW, a novel defense architecture that...

WordPress Slider‑Future 1.0.5 Exposure Scanner

This Metasploit auxiliary module is designed to detect exposure of the WordPress Slider‑Future plugin REST endpoint at /wp-json/slider-future/v1/upload-image/. The module performs a non-intrusive HTTP request OPTIONS method to determine whether the endpoint is accessible. It does not upload files...

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

Large language models LLMs are increasingly being deployed as software engineering agents that autonomously contribute to repositories. A major benefit these agents present is their ability to find and patch security vulnerabilities in the codebases they oversee. To estimate the capability of...

AWE: Adaptive Agents for Dynamic Web Penetration Testing

Modern web applications are increasingly produced through AI-assisted development and rapid no-code deployment pipelines, widening the gap between accelerating software velocity and the limited adaptability of existing security tooling. Pattern-driven scanners fail to reason about novel contexts,...

Power Network SCADA Quantum Communications: A Comparison of BB84, B92, E91, and SGS04 Quantum Key Distribution Protocols

The current state, emerging trends, and practical challenges of optical fiber-based power network SCADA quantum communication must be addressed to fully utilise the technological platform's potential in real-world power system SCADA communications involving massive volumes of real-time data, as...

Jailbreaking Embodied LLMs Via Action-Level Manipulation

Embodied Large Language Models LLMs enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with real-world actuation introduce a new vulnerability: instructions tha...

QSpy: A Quantum RAT for Circuit Spying and IP Theft

As quantum computing platforms increasingly adopt cloud-based execution, users submit quantum circuits to remote compilers and backends, trusting that what they submit is exactly what will be run. This shift introduces new trust assumptions in the submission pipeline, which remain largely...

Extending Adaptive Cruise Control with Machine Learning Intrusion Detection Systems

An Adaptive Cruise Control ACC system automatically adjusts the host vehicle's speed to maintain a safe following distance from a lead vehicle. In typical implementations, a feedback controller e.g., a Proportional-Integral-Derivative PID controller computes the host vehicle's acceleration using ...

On the Practical Feasibility of Harvest-Now, Decrypt-Later Attacks

Harvest-now, decrypt-later HN-DL attacks threaten today's encrypted communications by archiving ciphertext until a quantum computer can break the underlying key exchange. This paper reframes HN-DL as an economic problem, quantifying adversary costs across Transport Layer Security TLS 1.2, TLS 1.3...

Quantifying Frontier LLM Capabilities for Container Sandbox Escape

Large language models LLMs increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated in isolated "sandbox" environments, often implemented using...

ATLAS: AI-Assisted Threat-To-Assertion Learning for System-On-Chip Security Verification

This work presents ATLAS, an LLM-driven framework that bridges standardized threat modeling and property-based formal verification for System-on-Chip SoC security. Starting from vulnerability knowledge bases such as Common Weakness Enumeration CWE, ATLAS identifies SoC-specific assets, maps...

A Systematic Study of LLM-Based Architectures for Automated Patching

Large language models LLMs have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs, the field lacks a systematic comparison of patching...

VEcho: A Paradigm Shift from Vulnerability Verification to Proactive Discovery with Large Language Models

Static Application Security Testing SAST tools often suffer from high false positive rates, leading to alert fatigue that consumes valuable auditing resources. Recent efforts leveraging Large Language Models LLMs as filters offer limited improvements; however, these methods treat LLMs as passive,...

Security Is Not Enough: Privacy in Encryption Regulation and Lawful-Surveillance Protocols

This article argues that security is not enough to fully capture what is at stake in government exceptional access to encrypted data. A conception of privacy as security has little to say about "lawful-surveillance protocols'' -- an active research agenda in cryptography that aims to enable...

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents

Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However, the openness and rapid growth of these ecosystems often outpace systematic security evaluation. In this paper, we...

Time Stepped Cyber Physical Simulation of DoS, DoD, and FDI Attacks on the IEEE 14 Bus System

Reliable grid operation depends on accurate and timely telemetry, making modern power systems vulnerable to communication layer cyberattacks. This paper evaluates how Denial of Service DoS, Denial of Data DoD, and False Data Injection FDI attacks disrupt the IEEE 14 bus system using a MATLAB only...

IU: Imperceptible Universal Backdoor Attack

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal backdoor attac...

AMDS: Attack-Aware Multi-Stage Defense System for Network Intrusion Detection with Two-Stage Adaptive Weight Learning

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply uniform detection strategies, which may not account for...

How the Graph Construction Technique Shapes Performance in IoT Botnet Detection

The increasing incidence of IoT-based botnet attacks has driven interest in advanced learning models for detection. Recent efforts have focused on leveraging attention mechanisms to model long-range feature dependencies and Graph Neural Networks GNNs to capture relationships between data instance...

Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents

Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or vision language models operating on page screenshots. However, web pages often change between planning and execution, causing agents to execute action...

Darktrace Annual Threat Report 2026

The Darktrace Annual Threat Report 2026 reinforces a reality every CISO feels: the center of gravity isn't the perimeter, vulnerability management, or malware, but trust abused via identity. Their analysis found that nearly 70% of incidents in the Americas region begin with stolen or misused...

Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

Jailbreak techniques for large language models LLMs evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce JAILBREAK FOUNDRY JBF, a system that addresses this gap via a...

Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection

Cross-domain intrusion detection remains a critical challenge due to significant variability in network traffic characteristics and feature distributions across environments. This study evaluates the transferability of three widely used flow-based feature sets Argus, Zeek and CICFlowMeter across...

Neurosymbolic Learning for Advanced Persistent Threat Detection under Extreme Class Imbalance

The growing deployment of Internet of Things IoT devices in smart cities and industrial environments increases vulnerability to stealthy, multi-stage advanced persistent threats APTs that exploit wireless communication. Detection is challenging due to severe class imbalance in network traffic,...

Empowering Future Cybersecurity Leaders: Advancing Students through FINDS Education for Digital Forensic Excellence

The Forensics Investigations Network in Digital Sciences FINDS Research Center of Excellence CoE, funded by the U.S. Army Research Laboratory, advances Digital Forensic Engineering Education DFEE through an integrated research education framework for AI enabled cybersecurity workforce development...

Formal Analysis and Supply Chain Security for Agentic AI Skills

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw 228,000 GitHub stars and Anthropic Agent Skills 75,600 stars -- has introduced a critical supply chain attack surface. The ClawHavoc campaign January-February 2026 infiltrated over 1,200 malicious skills into the...

Quantifying Catastrophic Forgetting in IoT Intrusion Detection Systems

Distribution shifts in attack patterns within RPL-based IoT networks pose a critical threat to the reliability and security of large-scale connected systems. Intrusion Detection Systems IDS trained on static datasets often fail to generalize to unseen threats and suffer from catastrophic forgetti...

BeyondTrust RS 25.3.1 PRA/RS Mass Scanner

This Metasploit module is a safe auxiliary scanner for the Metasploit Framework designed to identify potentially vulnerable deployments of BeyondTrust Privileged Remote Access and BeyondTrust Remote Support that are susceptible to CVE-2026-1731...

Cryptographic Fragility of Standard Quantum Repeater Protocols

The security of the proposed quantum Internet relies on repeater protocols designed under the assumption of stochastic, characterizable noise. We demonstrate that in adversarial environments this assumption induces performance vulnerabilities for computationally bounded repeater nodes. We show th...

Cybersecurity of Teleoperated Quadruped Robots: A Systematic Survey of Vulnerabilities, Threats, and Open Defense Gaps

Teleoperated quadruped robots are increasingly deployed in safety-critical missions -- industrial inspection, military reconnaissance, and emergency response -- yet the security of their communication and control infrastructure remains insufficiently characterized. Quadrupeds present distinct...

OpenAI - Disrupting Malicious Uses of Our Models

This is the February, 2026 report from OpenAI that discusses their work in disrupting malicious use of their models...

RTSP Unauthenticated Stream Exposure Checker

This Python script uses the OpenCV library cv2 to test whether an IP camera exposes its RTSP stream without authentication. It attempts to connect to the default RTSP endpoint rtsp://:554/default and checks if the stream can be opened and a video frame retrieved successfully. If the connection...

ThreatFormer-IDS: Robust Transformer Intrusion Detection with Zero-Day Generalization and Explainable Attribution

Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels. Existing IDS solutions often report strong in-distribution accuracy, but they may degrade when evaluated ...

RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling

Seed explosion is a fundamental problem in fuzzing seed scheduling, where a fuzzer maintains a huge corpus and fails to choose promising seeds. Existing works focus on seed prioritization but still suffer from seed explosion since corpus size remains huge. We tackle this from a new perspective:...

Wireshark Analyzer 4.6.4

Wireshark is a GTK+-based network protocol analyzer that lets you capture and interactively browse the contents of network frames. The goal of the project is to create a commercial-quality analyzer for Unix and Win32 and to give Wireshark features that are missing from closed-source sniffers. Thi...

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection

We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Unlike traditional CAPTCHAs that distinguish humans from machines, our benchmark exploits a capability gap: model...

Eve'S Forgery Probability from Her False Acceptance Probability: Interactive Authentication, Holevo Information and the Min-Entropy

We obtain estimates for Eve's forgery probability, namely the probability that she is able to forge a message which Alice or Bob mistakenly accept over a noisy Quantum channel for generating a shared Quantum secret key. This probability is related to Eve's success probability obtained in a previo...

Strengthening Security and Noise Resistance in One-Way Quantum Key Distribution Protocols through Hypercube-Based Quantum Walks

Quantum Key Distribution QKD is a foundational cryptographic protocol that ensures information-theoretic security. However, classical protocols such as BB84, though favored for their simplicity, offer limited resistance to eavesdropping, and perform poorly under realistic noise conditions. Recent...

Blockchain-Enabled Routing for Zero-Trust Low-Altitude Intelligent Networks

Due to the scalability and portability, low-altitude intelligent networks LAINs are essential in various fields such as surveillance and disaster rescue. However, in LAINs, unmanned aerial vehicles UAVs are characterized by the distributed topology and high mobility, thus vulnerable to security...

Splunk Enterprise 8.2.9 / 9.0.2 Vulnerability Scanner

This is a scanner that checks if a Splunk Enterprise system is susceptible to CVE‑2022‑43571, an authenticated remote code execution vulnerability. The vulnerability exists due to insufficient input sanitization in SimpleXML dashboard style parameters such as lineColor or fillColor. When a...

Lifecycle-Integrated Security for AI-Cloud Convergence in Cyber-Physical Infrastructure

The convergence of Artificial Intelligence AI inference pipelines with cloud infrastructure creates a dual attack surface where cloud security standards and AI governance frameworks intersect without unified enforcement mechanisms. AI governance, cloud security, and industrial control system...

A High-Throughput AES-GCM Implementation on GPUs for Secure, Policy-Based Access to Massive Astronomical Catalogs

The era of large astronomical surveys generates massive image catalogs requiring efficient and secure access, particularly during pre-publication periods where data confidentiality and integrity are paramount. While Findable, Accessible, Interoperable, and Reusable FAIR principles guide the...

Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection under Resource Constraints

Distributed denial-of-service DDoS attacks threaten the availability of Internet of Things IoT infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising detection accuracy, their reliability, computational feasibility, a...