Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism Via Probabilistically Ablating Refusal Direction

Jailbreak attacks pose persistent threats to large language models LLMs. Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and unrobust internal defense mechanisms. These limitations make...

SecureFixAgent: a Hybrid LLM Agent for Automated Python Static Vulnerability Repair

Modern software development pipelines face growing challenges in securing large codebases with extensive dependencies. Static analysis tools like Bandit are effective at vulnerability detection but suffer from high false positives and lack repair capabilities. Large Language Models LLMs, in...

Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems

Extended reality XR applications increasingly integrate Large Language Models LLMs to enhance user experience, scene understanding, and even generate executable XR content, and are often called "AI glasses". Despite these potential benefits, the integrated XR-LLM pipeline makes XR applications...

Threat Modeling for Enhancing Security of IoT Audio Classification Devices under a Secure Protocols Framework

The rapid proliferation of IoT nodes equipped with microphones and capable of performing on-device audio classification exposes highly sensitive data while operating under tight resource constraints. To protect against this, we present a defence-in-depth architecture comprising a security protoco...

Orion: Fuzzing Workflow Automation

Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manu...

TOR Virtual Network Tunneling Tool 0.4.8.18

Tor is a network of virtual tunnels that allows people and groups to improve their privacy and security on the Internet. It also enables software developers to create new communication tools with built-in privacy features. It provides the foundation for a range of applications that allow...

Suricata IDPE 8.0.1

Suricata is a network intrusion detection and prevention engine developed by the Open Information Security Foundation and its supporting vendors. The engine is multi-threaded and has native IPv6 support. It's capable of loading existing Snort rules and signatures and supports the Barnyard and...

Security Analysis of Web Applications Based on Gruyere

With the rapid development of Internet technologies, web systems have become essential infrastructures for modern information exchange and business operations. However, alongside their expansion, numerous security vulnerabilities have emerged, making web security a critical research focus within...

Hybrid Deep Learning-Federated Learning Powered Intrusion Detection System for IoT/5G Advanced Edge Computing Network

The exponential expansion of IoT and 5G-Advanced applications has enlarged the attack surface for DDoS, malware, and zero-day intrusions. We propose an intrusion detection system that fuses a convolutional neural network CNN, a bidirectional LSTM BiLSTM, and an autoencoder AE bottleneck within a...

GNUnet P2P Framework 0.25.0

GNUnet is a peer-to-peer framework with focus on providing security. All peer-to-peer messages in the network are confidential and authenticated. The framework provides a transport abstraction layer and can currently encapsulate the network traffic in UDP IPv4 and IPv6, TCP IPv4 and IPv6, HTTP, o...

Beyond Classification: Evaluating LLMs for Fine-Grained Automatic Malware Behavior Auditing

Automated malware classification has achieved strong detection performance. Yet, malware behavior auditing seeks causal and verifiable explanations of malicious activities -- essential not only to reveal what malware does but also to substantiate such claims with evidence. This task is challengin...

A Survey and Evaluation Framework for Secure DNS Resolution

Since security was not among the original design goals of the Domain Name System herein called Vanilla DNS, many secure DNS schemes have been proposed to enhance the security and privacy of the DNS resolution process. Some proposed schemes aim to replace the existing DNS infrastructure entirely,...

The Cybersecurity of a Humanoid Robot

The rapid advancement of humanoid robotics presents unprecedented cybersecurity challenges that existing theoretical frameworks fail to adequately address. This report presents a comprehensive security assessment of a production humanoid robot platform, bridging the gap between abstract security...

LLM Jailbreak Detection for (Almost) Free!

Large language models LLMs enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak attacks through the assistance of other models or multiple model...

Cybersecurity AI: Humanoid Robots As Attack Vectors

We present a systematic security assessment of the Unitree G1 humanoid showing it operates simultaneously as a covert surveillance node and can be purposed as an active cyber operations platform. Partial reverse engineering of Unitree's proprietary FMX encryption reveal a static Blowfish-ECB laye...

ATLANTIS: AI-Driven Threat Localization, Analysis, and Triage Intelligence System

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge AIxCC at DEF CON 33 August 2025. AIxCC 2023-2025 challenged teams to build autonomous cyber reasoning systems capable of discovering and patching...

SLasH-DSA: Breaking SLH-DSA Using an Extensible End-To-End Rowhammer Framework

As quantum computing advances, PQC schemes are adopted to replace classical algorithms. Among them is the SLH-DSA that was recently standardized by NIST and is favored for its conservative security foundations. In this work, we present the first software-only universal forgery attack on SLH-DSA,...

A Graph-Based Approach to Alert Contextualisation in Security Operations Centres

Interpreting the massive volume of security alerts is a significant challenge in Security Operations Centres SOCs. Effective contextualisation is important, enabling quick distinction between genuine threats and benign activity to prioritise what needs further analysis.This paper proposes a...

Bridging Threat Models and Detections: Formal Verification Via CADP

Threat detection systems rely on rule-based logic to identify adversarial behaviors, yet the conformance of these rules to high-level threat models is rarely verified formally. We present a formal verification framework that models both detection logic and attack trees as labeled transition syste...

Suricata IDPE 7.0.12

Suricata is a network intrusion detection and prevention engine developed by the Open Information Security Foundation and its supporting vendors. The engine is multi-threaded and has native IPv6 support. It's capable of loading existing Snort rules and signatures and supports the Barnyard and...

XOffense: an AI-Driven Autonomous Penetration Testing Framework with Offensive Knowledge-Enhanced LLMs and Multi Agent Systems

This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense...

GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?

As software development practices increasingly adopt AI-powered tools, ensuring that such tools can support secure coding has become critical. This study evaluates the effectiveness of GitHub Copilot's recently introduced code review feature in detecting security vulnerabilities. Using a curated...

Characterizing Phishing Pages by JavaScript Capabilities

In 2024, the Anti-Phishing Work Group identified over one million phishing pages. Phishers achieve this scale by using phishing kits -- ready-to-deploy phishing websites -- to rapidly deploy phishing campaigns with specific data exfiltration, evasion, or mimicry techniques. In contrast, researche...

OpenSSL Toolkit 3.5.3

OpenSSL is a robust, fully featured Open Source toolkit implementing the Secure Sockets Layer and Transport Layer Security protocols with full-strength cryptography world-wide. This is the 3.5 release...

Digital Sovereignty Control Framework for Military AI-Based Cyber Security

In today's evolving threat landscape, ensuring digital sovereignty has become mandatory for military organizations, especially given their increased development and investment in AI-driven cyber security solutions. To this end, a multi-angled framework is proposed in this article in order to defi...

Hierarchical Deep Fusion Framework for Multi-Dimensional Facial Forgery Detection - the 2024 Global Deepfake Image Detection Challenge

The proliferation of sophisticated deepfake technology poses significant challenges to digital security and authenticity. Detecting these forgeries, especially across a wide spectrum of manipulation techniques, requires robust and generalized models. This paper introduces the Hierarchical Deep...

Invisible Ears at Your Fingertips: Acoustic Eavesdropping Via Mouse Sensors

Modern optical mouse sensors, with their advanced precision and high responsiveness, possess an often overlooked vulnerability: they can be exploited for side-channel attacks. This paper introduces Mic-E-Mouse, the first-ever side-channel attack that targets high-performance optical mouse sensors...

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs

Code-generating Large Language Models LLMs significantly accelerate software development. However, their frequent generation of insecure code presents serious risks. We present a comprehensive evaluation of seven parameter-efficient fine-tuning PEFT techniques, demonstrating substantial gains in...

Cyber Attack Mitigation Framework for Denial of Service (DoS) Attacks in Fog Computing

Innovative solutions to cyber security issues are shaped by the ever-changing landscape of cyber threats. Automating the mitigation of these threats can be achieved through a new methodology that addresses the domain of mitigation automation, which is often overlooked. This literature overview...

Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: a 2022 Study of GPT-3 and Contemporary Models

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two adversarial attacks against Large Language Models LLMs: promp...

Ensembling Large Language Models for Code Vulnerability Detection: an Empirical Evaluation

Code vulnerability detection is crucial for ensuring the security and reliability of modern software systems. Recently, Large Language Models LLMs have shown promising capabilities in this domain. However, notable discrepancies in detection results often arise when analyzing identical code segmen...

Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning

Industrial control systems ICSs are widely used in industry, and their security and stability are very important. Once the ICS is attacked, it may cause serious damage. Therefore, it is very important to detect anomalies in ICSs. ICS can monitor and manage physical devices remotely using...

An Unsupervised Learning Approach for a Reliable Profiling of Cyber Threat Actors Reported Globally Based on Complete Contextual Information of Cyber Attacks

Cyber attacks are rapidly increasing with the advancement of technology and there is no protection for our information. To prevent future cyberattacks it is critical to promptly recognize cyberattacks and establish strong defense mechanisms against them. To respond to cybersecurity threats...

Cyber Threat Hunting: Non-Parametric Mining of Attack Patterns from Cyber Threat Intelligence for Precise Threats Attribution

With the ever-changing landscape of cyber threats, identifying their origin has become paramount, surpassing the simple task of attack classification. Cyber threat attribution gives security analysts the insights they need to device effective threat mitigation strategies. Such strategies empower...

Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: a Multi-Robot Patrol Case Study

Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes...

A Practical Adversarial Attack against Sequence-Based Deep Learning Malware Classifiers

Sequence-based deep learning models e.g., RNNs, can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence characteristics of behavior sequences to deceive malware...

LOKI: Proactively Discovering Online Scam Websites by Mining Toxic Search Queries

Online e-commerce scams, ranging from shopping scams to pet scams, globally cause millions of dollars in financial damage every year. In response, the security community has developed highly accurate detection systems able to determine if a website is fraudulent. However, finding candidate scam...

Exploiting Timing Side-Channels in Quantum Circuits Simulation Via ML-Based Methods

As quantum computing advances, quantum circuit simulators serve as critical tools to bridge the current gap caused by limited quantum hardware availability. These simulators are typically deployed on cloud platforms, where users submit proprietary circuit designs for simulation. In this work, we...

Collaborative P4-SDN DDoS Detection and Mitigation with Early-Exit Neural Networks

Distributed Denial of Service DDoS attacks pose a persistent threat to network security, requiring timely and scalable mitigation strategies. In this paper, we propose a novel collaborative architecture that integrates a P4-programmable data plane with an SDN control plane to enable real-time DDo...

SoK: How Sensor Attacks Disrupt Autonomous Vehicles: an End-To-End Analysis, Challenges, and Missed Threats

Autonomous vehicles, including self-driving cars, robotic ground vehicles, and drones, rely on complex sensor pipelines to ensure safe and reliable operation. However, these safety-critical systems remain vulnerable to adversarial sensor attacks that can compromise their performance and mission...

Thunderhammer: Rowhammer Bitflips Via PCIe and Thunderbolt (USB-C)

In recent years, Rowhammer has attracted significant attention from academia and industry alike. This technique, first published in 2014, flips bits in memory by repeatedly accessing neighbouring memory locations. Since its discovery, researchers have developed a substantial body of work exploiti...

Your Compiler Is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers

Deep learning DL compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified compiler alter a model's semantics during compilation and...

DMLDroid: Deep Multimodal Fusion Framework for Android Malware Detection with Resilience to Code Obfuscation and Adversarial Perturbations

In recent years, learning-based Android malware detection has seen significant advancements, with detectors generally falling into three categories: string-based, image-based, and graph-based approaches. While these methods have shown strong detection performance, they often struggle to sustain...

Realistic Environmental Injection Attacks on GUI Agents

GUI agents built on LVLMs are increasingly used to interact with websites. However, their exposure to open-world content makes them vulnerable to Environmental Injection Attacks EIAs that hijack agent behavior via webpage elements. Many recent studies assume the attacker to be a regular user who...

ENJ: Optimizing Noise with Genetic Algorithms to Jailbreak LSMs

The widespread application of Large Speech Models LSMs has made their security risks increasingly prominent. Traditional speech adversarial attack methods face challenges in balancing effectiveness and stealth. This paper proposes Evolutionary Noise Jailbreak ENJ, which utilizes a genetic algorit...

Exploring and Exploiting the Resource Isolation Attack Surface of WebAssembly Containers

Recently, the WebAssembly or Wasm technology has been rapidly evolving, with many runtimes actively under development, providing cross-platform secure sandboxes for Wasm modules to run as portable containers. Compared with Docker, which isolates applications at the operating system level, Wasm...

ODoQ: Oblivious DNS-Over-QUIC

The Domain Name System DNS, which converts domain names to their respective IP addresses, has advanced enhancements aimed at safeguarding DNS data and users' identity from attackers. The recent privacy-focused advancements have enabled the IETF to standardize several protocols. Nevertheless, thes...

From Firewalls to Frontiers: AI Red-Teaming Is a Domain-Specific Evolution of Cyber Red-Teaming

A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI, red-teaming will need to evolve to address the unique vulnerabilities and risks posed by AI systems. We take the...

VulAgent: Hypothesis-Validation Based Multi-Agent Vulnerability Detection

The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program context. We present VulAgent, a multi-agent vulnerability...

Weakly Supervised Vulnerability Localization Via Multiple Instance Learning

Software vulnerability detection has emerged as a significant concern in the field of software security recently, capturing the attention of numerous researchers and developers. Most previous approaches focus on coarse-grained vulnerability detection, such as at the function or file level. Howeve...