Adaptive Instruction Composition for Automated LLM Red-Teaming

Many approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target. Several of them task the attacker with identifying effective strategies through trial and error, resulting in a semantically limited range of successes. Another approach discovers diverse attacks ...

Threat Detection and Resilience Techniques in PRS-Assisted OTDOA 5G Positioning Systems

Precise positioning is a key enabler for emerging 5G applications, from autonomous transport to industrial automation. Yet the open physical layer PL leaves standard positioning reference signals PRSs vulnerable to manipulation. This work addresses the security of downlink observed time differenc...

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs

Logging code plays an important role in software systems by recording key events and behaviors, which are essential for debugging and monitoring. However, insecure logging practices can inadvertently expose sensitive information or enable attacks such as log injection, posing serious threats to...

ATBroker Registry Security Scanner

This code is a defensive Windows security scanner designed to audit potentially sensitive Registry paths related to ATBroker Accessibility Technology Broker and core system hives. It only checks for the presence of certain registry keys to see if they're protected or accessible...

Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models remains susceptible to formally characterizable arithmetic vulnerabilities. Anthropic has not publicly characterized the escape vector; some secondary...

An Analysis of Attack Vectors against FIDO2 Authentication

Phishing attacks remain one of the most prevalent threats to online security, with the Anti-Phishing Working Group reporting over 890,000 attacks in Q3 2025 alone. Traditional password-based authentication is particularly vulnerable to such attacks, prompting the development of more secure...

Rosemary 1.0.2

Rosemary is a cross-platform transparent tunneling platform designed for network pivoting. Unlike traditional tools that rely on TUN/TAP interfaces or require per-application proxy configuration like proxychains, Rosemary intercepts traffic at the kernel level...

PVAC: A RowHammer Mitigation Architecture Exploiting Per-Victim-Row Counting

As DRAM scaling exacerbates RowHammer, DDR5 introduces per-row activation counting PRAC to track aggressor activity. However, PRAC indiscriminately increments counters on every activation -- including benign refreshes -- while relying solely on explicit RFM operations for resets. Consequently,...

DNG File Generator for Security Testing Masked RGB Tables

This Python script is a research-oriented DNG Digital Negative file generator designed to build a specially crafted image file with controlled metadata structures for security testing of DNG processing engines...

Towards Certified Malware Detection: Provable Guarantees against Evasion Attacks

Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose a certifiably robust malware detection framework based on randomized smoothing through feature ablation and targeted...

Revisiting and Expanding the IPv6 Network Periphery: Global-Scale Measurement and Security Analysis

As IPv6 deployment accelerates, understanding the evolving security posture of network peripheries becomes increasingly important. A DSN 2021 study introduced the first large-scale discovery of IPv6 network peripheries, uncovering risks like service exposure and routing loops. However, its scope...

Rosemary 1.0.1

Rosemary is a cross-platform transparent tunneling platform designed for network pivoting. Unlike traditional tools that rely on TUN/TAP interfaces or require per-application proxy configuration like proxychains, Rosemary intercepts traffic at the kernel level...

DNG File Fuzzer for Robustness

This Python script is a mutation-based fuzzing tool designed to test the robustness of DNG Digital Negative / TIFF-based file parsers by generating large numbers of corrupted or semi-valid image files. It works by starting from a minimal valid DNG structure, then applying random mutations to...

Adding Compilation Metadata to Binaries to Make Disassembly Decidable

The binary executable format is the standard method for distributing and executing software. Yet, it is also as opaque a representation of software as can be. If the binary format were augmented with metadata that provides security-relevant information, such as which data is intended by the...

I2P 2.12.0

I2P is an anonymizing network, offering a simple layer that identity-sensitive applications can use to securely communicate. All data is wrapped with several layers of encryption, and the network is both distributed and dynamic, with no trusted parties. This is the source code release version...

Adobe DNG File Security Scanner

This program is a defensive security tool designed to analyze DNG Digital Negative image files and detect potential signs of malicious manipulation or exploit attempts. It performs a low-level inspection of the file structure by parsing the TIFF header and scanning raw binary content for suspicio...

Understanding Password Preferences, Memorability, and Security through a Human-Centered Lens

Passwords remain the primary authentication method, yet user-created passwords are often the weakest due to the security-usability trade-off. Although AI-based password generators are emerging, little is known about their effectiveness and user perceptions. This eye-tracking study examined how...

We Are Currently Clean on OPSEC: Why JD Can't Encrypt

We analyse the 2025 Signalgate leak of sensitive US military information by the Trump administration, addressing why confidentiality was violated messages leaked to the press in spite of encryption Signal, to deepen the socio-technical considerations when designing and deploying encryption. First...

API Security Based on Automatic OpenAPI Mapping

This paper presents Map Reduce Graph MRG, a novel unsupervised method for modeling and securing HTTP REST APIs. MRG learns API structure from real-world traffic without prior knowledge or labels, automatically generating OpenAPI-compliant documentation by reconstructing routes, methods, and...

Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges

Large Language Model LLM agents are increasingly proposed for autonomous cybersecurity tasks, but their capabilities in realistic offensive settings remain poorly understood. We present DeepRed, an open-source benchmark for evaluating LLM-based agents on realistic Capture The Flag CTF challenges ...

Camaleon CMS 2.9.1 Automated Admin Login, Version Detection, and Profile Update Script

This is a version detection and profile updating script for Camaleon CMS. It does not exploit any issue but can be useful for security testing to see if a vulnerable version is in use...

DP-FlogTinyLLM: Differentially Private Federated Log Anomaly Detection Using Tiny LLMs

Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world settings, these logs are often distributed across multiple organizations and cannot be centralized due to privacy and security constraints. Existing...

Insights into Security-Related AI-Generated Pull Requests

Recent years have experienced growing contributions of AI coding agents that assist human developers in various software engineering tasks. However, this growing AI-assisted autonomy raises questions about security and trust. In this paper, we analyze more than 33,000 AI-generated pull requests P...

An AI Agent Execution Environment to Safeguard User Data

AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data e.g., personal and financial information. This poses a serious risk to security and privacy. Adversaries may attack the AI model e.g., via prompt injection to...

Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model LLM agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or hints, identify the exact timestamps of malicious events. The...

FreeBSD Security Advisory - FreeBSD-SA-26:11.amd64

FreeBSD Security Advisory - In order to apply a particular protection key to an address range, the kernel must update the corresponding page table entries. The subroutine which handled this failed to take into account the presence of 1GB largepage mappings created using the shmcreatelargepage3...

FreeBSD Security Advisory - FreeBSD-SA-26:10.tty

FreeBSD Security Advisory - The implementation of TIOCNOTTY failed to clear a back-pointer from the structure representing the controlling terminal to the calling process' session. If the invoking process then exits, the terminal structure may end up containing a pointer to freed memory. A...

AgentSOC: A Multi-Layer Agentic AI Framework for Security Operations Automation

Security Operations Centers SOCs increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a multi-layered agentic AI framework that enhances SOC...

Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection

Cross-site scripting XSS remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its behavior. These transformations make it difficult for traditional and machine learning-based detection systems to reliab...

AppleSEPKeyStore iOS macOS 26.1–26.2 Multi-Thread Race Condition Simulation Tool

This C/Objective-C program is a lightweight concurrency stress-testing tool designed to simulate and observe race conditions using atomic operations and multiple threads. It models a simplified shared-state system where concurrent readers and writers continuously interact with a shared variable...

Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4

Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning IICL, an attack class that uses abstract operator framing with few-shot...

Nuclei 3.8.0

Nuclei is a modern, high-performance vulnerability scanner that leverages simple YAML-based templates. It empowers you to design custom vulnerability detection scenarios that mimic real-world conditions, leading to zero false positives...

MetInfo CMS 8.1 XML Endpoint Behavior Analysis Tool

This script is a PHP-based analysis tool designed to interact with MetInfo CMS 8.1 endpoints through an XML-based interface. It uses cURL to send structured requests to a specific MetInfo module endpoint and evaluates the HTTP responses for basic fingerprinting indicators such as known keywords a...

TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs

Software vulnerabilities remain one of the most persistent threats to modern digital infrastructure. While static application security testing SAST tools have long served as the first line of defense, they suffer from high false-positive rates. This article presents TitanCA, a collaborative proje...

Enhancing Anomaly-Based Intrusion Detection Systems with Process Mining

Anomaly-based Intrusion Detection Systems IDSs ensure protection against malicious attacks on networked systems. While deep learning-based IDSs achieve effective performance, their limited trustworthiness due to black-box architectures remains a critical constraint. Despite existing explainable...

Weaponizing the Commons: A Taxonomy and Detection Framework of Abuse on GitHub

GitHub plays a critical role in modern software supply chains, making its security an important research concern. Existing studies have primarily focused on CI/CD automation, collaboration patterns, and community management, while abuse behaviors on GitHub have received little systematic...

BinDiff 8

BinDiff is an open-source comparison tool for binary files to quickly find differences and similarities in disassembled code...

CodeQL 2.25.2

Discover vulnerabilities across a codebase with CodeQL, an industry-leading semantic code analysis engine. CodeQL lets you query code as though it were data. Write a query to find all variants of a vulnerability, eradicating it forever. Then share your query to help others do the same...

Zeek 8.0.7

Zeek is a powerful network analysis framework that is much different from the typical IDS you may know. While focusing on network security monitoring, Zeek provides a comprehensive platform for more general network traffic analysis as well. Well grounded in more than 15 years of research, Zeek ha...

Joern 4.0.524

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

angr 9.2.211

angr is an open-source binary analysis platform for Python. It combines both static and dynamic symbolic "concolic" analysis, providing tools to solve a variety of tasks...

AppleSEPKeyStore Race Condition Emulator

Python script that emulates identify race conditions related to AppleSEPKeyStore. It is not an exploit. It simulates a shared object KernelObject, and uses threads to mimic concurrent access, premature free alive = False, and flags a UAF-like condition when accessing a logically freed object...

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm cybercrime, harassment, weapon synthesis, leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI...

ARES: Adaptive Red-Teaming and End-To-End Repair of Policy-Reward System

Reinforcement Learning from Human Feedback RLHF is central to aligning Large Language Models LLMs, yet it introduces a critical vulnerability: an imperfect Reward Model RM can become a single point of failure when it fails to penalize unsafe behaviors. While existing red-teaming approaches...

AppleSEPKeyStore Stress Tester / Fuzzer

This code is not a fully functional exploit, but rather a concurrency stress test and race-condition trigger targeting the Apple Secure Enclave key management driver AppleSEPKeyStore...

Towards Optimal Agentic Architectures for Offensive Security Tasks

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an empirical systems question. We introduce a controlled...

ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks

Intrusion detection systems IDSs for 5G networks must handle complex, high-volume traffic. Although opaque "black-box" models can achieve high accuracy, their lack of transparency hinders trust and effective operational response. We propose ExAI5G, a framework that prioritizes interpretability by...

Security Is Relative: Training-Free Vulnerability Detection Via Multi-Agent Behavioral Contract Synthesis

Deep learning for vulnerability detection has shown promising results on early benchmarks, but recent evaluations reveal catastrophic degradation: models achieving F1 0.68 on legacy datasets collapse to 0.031 under strict deduplication. We identify the root cause as the semantic ambiguity problem...

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs

Large Language Models LLMs have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN...

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending against TOCTOU Attacks on Computer-Use Agents

GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap mean 6.51 s on real OSWorld workloads creates a Time-Of-Check, Time-Of-Use TOCTOU window during which an unprivileged attacker can manipulate the UI state...