Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees

Recent advances in Large Language Models LLMs have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM agents for penetration testing primarily rely on self-guid...

An Ethically Grounded LLM-Based Approach to Insider Threat Synthesis and Detection

Insider threats are a growing organizational problem due to the complexity of identifying their technical and behavioral elements. A large research body is dedicated to the study of insider threats from technological, psychological, and educational perspectives. However, research in this domain h...

Signal-Based Malware Classification Using 1D CNNs

Malware classification is a contemporary and ongoing challenge in cyber-security: modern obfuscation techniques are able to evade traditional static analysis, while dynamic analysis is too resource intensive to be deployed at a large scale. One prominent line of research addresses these limitatio...

A Simple Data Exfiltration Game

Data exfiltration is a growing problem for business who face costs related to the loss of confidential data as well as potential extortion. This work presents a simple game theoretic model of network data exfiltration. In the model, the attacker chooses the exfiltration route and speed, and the...

Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment

Due to hardware and software improvements, an increasing number of AI models are deployed on-device. This shift enhances privacy and reduces latency, but also introduces security risks distinct from traditional software. In this article, we examine these risks through the real-world case study of...

The Signalgate Case Is Waiving a Red Flag to All Organizational and Behavioral Cybersecurity Leaders, Practitioners, and Researchers: Are We Receiving the Signal Amidst the Noise?

The Signalgate incident of March 2025, wherein senior US national security officials inadvertently disclosed sensitive military operational details via the encrypted messaging platform Signal, highlights critical vulnerabilities in organizational security arising from human error, governance gaps...

All You Need Is a Fuzzing Brain: an LLM-Powered System for Automated Vulnerability Detection and Patching

Our team, All You Need Is A Fuzzing Brain, was one of seven finalists in DARPA's Artificial Intelligence Cyber Challenge AIxCC, placing fourth in the final round. During the competition, we developed a Cyber Reasoning System CRS that autonomously discovered 28 security vulnerabilities - including...

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Jailbreak attacks on Large Language Models LLMs have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are designed to avoid. Among these, Greedy Coordinate Gradient GCG has emerged as a general and effective approach that...

Contrastive Self-Supervised Network Intrusion Detection Using Augmented Negative Pairs

Network intrusion detection remains a critical challenge in cybersecurity. While supervised machine learning models achieve state-of-the-art performance, their reliance on large labelled datasets makes them impractical for many real-world applications. Anomaly detection methods, which train...

LLMs in Cybersecurity: Friend or Foe in the Human Decision Loop?

Large Language Models LLMs are transforming human decision-making by acting as cognitive collaborators. Yet, this promise comes with a paradox: while LLMs can improve accuracy, they may also erode independent reasoning, promote over-reliance and homogenize decisions. In this paper, we investigate...

Network-Level Censorship Attacks in the InterPlanetary File System

The InterPlanetary File System IPFS has been successfully established as the de facto standard for decentralized data storage in the emerging Web3. Despite its decentralized nature, IPFS nodes, as well as IPFS content providers, have converged to centralization in large public clouds...

Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities

Traditional Artificial Intelligence AI approaches in cybersecurity exhibit fundamental limitations: inadequate conceptual grounding leading to non-robustness against novel attacks; limited instructibility impeding analyst-guided adaptation; and misalignment with cybersecurity objectives...

VehiclePassport: a GAIA-X-Aligned, Blockchain-Anchored Privacy-Preserving, Zero-Knowledge Digital Passport for Smart Vehicles

Modern vehicles accumulate fragmented lifecycle records across OEMs, owners, and service centers that are difficult to verify and prone to fraud. We propose VehiclePassport, a GAIA-X-aligned digital passport anchored on blockchain with zero-knowledge proofs ZKPs for privacy-preserving verificatio...

ALPHA: LLM-Enabled Active Learning for Human-Free Network Anomaly Detection

Network log data analysis plays a critical role in detecting security threats and operational anomalies. Traditional log analysis methods for anomaly detection and root cause analysis rely heavily on expert knowledge or fully supervised learning models, both of which require extensive labeled dat...

Measuring the Vulnerability Disclosure Policies of AI Vendors

As AI is increasingly integrated into products and critical systems, researchers are paying greater attention to identifying related vulnerabilities. Effective remediation depends on whether vendors are willing to accept and respond to AI vulnerability reports. In this paper, we examine the...

Asymmetry Vulnerability and Physical Attacks on Online Map Construction for Autonomous Driving

High-definition maps provide precise environmental information essential for prediction and planning in autonomous driving systems. Due to the high cost of labeling and maintenance, recent research has turned to online HD map construction using onboard sensor data, offering wider coverage and mor...

Schrodinger'S Toolbox: Exploring the Quantum Rowhammer Attack

Residual cross-talk in superconducting qubit devices creates a security vulnerability for emerging quantum cloud services. We demonstrate a Clifford-only Quantum Rowhammer attack-using just X and CNOT gates-that injects faults on IBM's 127-qubit Eagle processors without requiring pulse-level...

Decoding Latent Attack Surfaces in LLMs: Prompt Injection Via HTML in Web Summarization

Large Language Models LLMs are increasingly integrated into web-based systems for content summarization, yet their susceptibility to prompt injection attacks remains a pressing concern. In this study, we explore how non-visible HTML elements such as , aria-label, and alt attributes can be exploit...

Reasoning Introduces New Poisoning Attacks yet Makes Them More Complicated

Early research into data poisoning attacks against Large Language Models LLMs demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the intermediate chain-of-thought CoT and its inherent trait of...

EchoLeak: the First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Large language model LLM assistants are increasingly integrated into enterprise workflows, raising new security concerns as they bridge internal and external data sources. This paper presents an in-depth case study of EchoLeak CVE-2025-32711, a zero-click prompt injection vulnerability in Microso...

FuzzBox: Blending Fuzzing into Emulation for Binary-Only Embedded Targets

Coverage-guided fuzzing has been widely applied to address zero-day vulnerabilities in general-purpose software and operating systems. This approach relies on instrumenting the target code at compile time. However, applying it to industrial systems remains challenging, due to proprietary and...

Wrangling Entropy: Next-Generation Multi-Factor Key Derivation, Credential Hashing, and Credential Generation Functions

The Multi-Factor Key Derivation Function MFKDF offered a novel solution to the classic problem of usable client-side key management by incorporating multiple popular authentication factors into a key derivation process, but was later shown to be vulnerable to cryptanalysis that degraded its...

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs

Large Language Models LLMs have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like responses, leading to their integration across diverse domains,...

Robust DDoS-Attack Classification with 3D CNNs against Adversarial Methods

Distributed Denial-of-Service DDoS attacks remain a serious threat to online infrastructure, often bypassing detection by altering traffic in subtle ways. We present a method using hive-plot sequences of network data and a 3D convolutional neural network 3D CNN to classify DDoS traffic with high...

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System

LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt TIP, which...

Wapiti Web Application Vulnerability Scanner 3.2.5 Source Code

Wapiti is a web application vulnerability scanner. It will scan the web pages of a deployed web application and will fuzz the URL parameters and forms to find common web vulnerabilities. This is the source code release...

Jamming Smarter, Not Harder: Exploiting O-RAN Y1 RAN Analytics for Efficient Interference

The Y1 interface in O-RAN enables the sharing of RAN Analytics Information RAI between the near-RT RIC and authorized Y1 consumers, which may be internal applications within the operator's trusted domain or external systems accessing data through a secure exposure function. While this visibility...

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models

Large Language Models LLMs are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety mechanisms. Unlike overt attacks, these subtle prompts exploit...

From Protest to Power Plant: Interpreting the Role of Escalatory Hacktivism in Cyber Conflict

Since 2022, hacktivist groups have escalated their tactics, expanding from distributed denial-of-service attacks and document leaks to include targeting operational technology OT. By 2024, attacks on the OT of critical national infrastructure CNI had been linked to partisan hacktivist efforts in...

Wapiti Web Application Vulnerability Scanner 3.2.5

Wapiti is a web application vulnerability scanner. It will scan the web pages of a deployed web application and will fuzz the URL parameters and forms to find common web vulnerabilities. This is the binary release...

Cryptographic Application of Elliptic Curve with High Rank

Elliptic curve cryptography is better than traditional cryptography based on RSA and discrete logarithm of finite field in terms of efficiency and security. In this paper, we show how to exploit elliptic curve with high rank, which has not been used in cryptography before, to construct...

Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs

As large language models transition to agentic systems, current safety evaluation frameworks face critical gaps in assessing deployment-specific risks. We introduce AgentSeer, an observability-based evaluation framework that decomposes agentic executions into granular action and component graphs,...

FuzzRDUCC: Fuzzing with Reconstructed Def-Use Chain Coverage

Binary-only fuzzing often struggles with achieving thorough code coverage and uncovering hidden vulnerabilities due to limited insight into a program's internal dataflows. Traditional grey-box fuzzers guide test case generation primarily using control flow edge coverage, which can overlook bugs n...

A Transformer-BiGRU-Based Framework with Data Augmentation and Confident Learning for Network Intrusion Detection

In today's fast-paced digital communication, the surge in network traffic data and frequency demands robust and precise network intrusion solutions. Conventional machine learning methods struggle to grapple with complex patterns within the vast network intrusion datasets, which suffer from data...

A Kolmogorov-Arnold Network for Interpretable Cyberattack Detection in AGC Systems

Automatic Generation Control AGC is essential for power grid stability but remains vulnerable to stealthy cyberattacks, such as False Data Injection Attacks FDIAs, which can disturb the system's stability while evading traditional detection methods. Unlike previous works that relied on blackbox...

Bi-Level Game-Theoretic Planning of Cyber Deception for Cognitive Arbitrage

Cognitive vulnerabilities shape human decision-making and arise primarily from two sources: 1 cognitive capabilities, which include disparities in knowledge, education, expertise, or access to information, and 2 cognitive biases, such as rational inattention, confirmation bias, and base rate...

What Is Cybersecurity in Space?

Satellites, drones, and 5G space links now support critical services such as air traffic, finance, and weather. Yet most were not built to resist modern cyber threats. Ground stations can be breached, GPS jammed, and supply chains compromised, while no shared list of vulnerabilities or safe testi...

Where Have All the Firewalls Gone? Security Consequences of Residential IPv6 Transition

IPv4 NAT has limited the spread of IoT botnets considerably by default-denying bots' incoming connection requests to in-home devices unless the owner has explicitly allowed them. As the Internet transitions to majority IPv6, however, residential connections no longer require the use of NAT. This...

Quantum AI Algorithm Development for Enhanced Cybersecurity: a Hybrid Approach to Malware Detection

This study explores the application of quantum machine learning QML algorithms to enhance cybersecurity threat detection, particularly in the classification of malware and intrusion detection within high-dimensional datasets. Classical machine learning approaches encounter limitations when dealin...

Systematic Timing Leakage Analysis of NIST PQDSS Candidates: Tooling and Lessons Learned

The PQDSS standardization process requires cryptographic primitives to be free from vulnerabilities, including timing and cache side-channels. Resistance to timing leakage is therefore an essential property, and achieving this typically relies on software implementations that follow constant-time...

KubeGuard: LLM-Assisted Kubernetes Hardening Via Configuration Files and Runtime Logs Analysis

The widespread adoption of Kubernetes K8s for orchestrating cloud-native applications has introduced significant security challenges, such as misconfigured resources and overly permissive configurations. Failing to address these issues can result in unauthorized access, privilege escalation, and...

SREC: Encrypted Semantic Super-Resolution Enhanced Communication

Semantic communication SemCom, as a typical paradigm of deep integration between artificial intelligence AI and communication technology, significantly improves communication efficiency and resource utilization efficiency. However, the security issues of SemCom are becoming increasingly prominent...

ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in Shielding Memory System

Intel SGX and hypervisors isolate non-privileged programs from other software, ensuring confidentiality and integrity. However, side-channel attacks continue to threaten Intel SGX's security, enabling malicious OS to manipulate PTE present bits, induce page faults, and steal memory access traces...

Revisiting Third-Party Library Detection: a Ground Truth Dataset and Its Implications across Security Tasks

Accurate detection of third-party libraries TPLs is fundamental to Android security, supporting vulnerability tracking, malware detection, and supply chain auditing. Despite many proposed tools, their real-world effectiveness remains unclear.We present the first large-scale empirical study of ten...

Constructing a Photonic Implementation of Quantum Key Distribution

Quantum Key Distribution QKD stands as a revolutionary approach to secure communication, using the principles of quantum mechanics to establish unbreakable channels. Unlike traditional cryptography, which relies on the computational difficulty of mathematical problems, QKD utilizes the inherent...

An Empirical Study of Vulnerabilities in Python Packages and Their Detection

In the rapidly evolving software development landscape, Python stands out for its simplicity, versatility, and extensive ecosystem. Python packages, as units of organization, reusability, and distribution, have become a pressing concern, highlighted by the considerable number of vulnerability...

False Sense of Security: Why Probing-Based Malicious Input Detection Fails to Generalize

Large Language Models LLMs can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in LLMs' internal representations, and researchers ha...

ICSLure: a Very High Interaction Honeynet for PLC-Based Industrial Control Systems

The security of Industrial Control Systems ICSs is critical to ensuring the safety of industrial processes and personnel. The rapid adoption of Industrial Internet of Things IIoT technologies has expanded system functionality but also increased the attack surface, exposing ICSs to a growing range...

Adversarial Bug Reports As a Security Risk in Language Model-Based Automated Program Repair

Large Language Model LLM - based Automated Program Repair APR systems are increasingly integrated into modern software development workflows, offering automated patches in response to natural language bug reports. However, this reliance on untrusted user input introduces a novel and underexplored...

Breaking to Build: a Threat Model of Prompt-Based Attacks for Securing LLMs

The proliferation of Large Language Models LLMs has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks exploit vulnerabilities in a model's design, training, and...