The Impact of AI on the Cyber Offense-Defense Balance and the Character of Cyber Conflict

Unlike other domains of conflict, and unlike other fields with high anticipated risk from AI, the cyber domain is intrinsically digital with a tight feedback loop between AI training and cyber application. Cyber may have some of the largest and earliest impacts from AI, so it is important to...

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Augmented Reality AR and Multimodal Large Language Models LLMs are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility...

Measuring Computational Universality of Fully Homomorphic Encryption

Many real-world applications, such as machine learning and graph analytics, involve combinations of linear and non-linear operations. As these applications increasingly handle sensitive data, there is a significant demand for privacy-preserving computation techniques capable of efficiently...

Creating Scripts to Identify Vulnerable FTPs

This whitepaper covers how to create Nmap scripts to identify banners and versions of FTP servers. It also covers methods to mitigate the public visibility of banners and version information on FTP servers. Written in Portuguese...

SPA: Securing Persistent LLM Agents across Queries with Plan-First Information-Flow Control

Large language model LLM agents increasingly operate over untrusted webpages, documents, tools, and persistent states while exercising authority over security-sensitive resources. Existing defenses typically protect either planning or individual tool interactions, but persistent agents face a...

Ubuntu Security Notice USN-8640-1

Ubuntu Security Notice 8640-1 - It was discovered that Engrampa incorrectly handled symbolic links when extracting certain archives. An attacker could possibly use this issue to write arbitrary files and execute arbitrary code...

Capability-Based Planning for AI Crisis Preparedness

Capability-based planning drives preparedness in defense and homeland security, but has yet to be applied seriously to AI. Government AI preparations follow a predict-then-act paradigm: rank risks by likelihood and impact, then prepare for the highest expected harm. AI resists prediction: expert...

Red Hat Security Advisory 2026-55772-03

Red Hat Security Advisory 2026-55772-03 - An update for haproxy is now available for Red Hat Enterprise Linux 9. Issues addressed include denial of service and integer overflow vulnerabilities...

Red Hat Security Advisory 2026-54580-03

Red Hat Security Advisory 2026-54580-03 - Red Hat OpenShift Container Platform release 4.20.34 is now available with updates to packages and images that fix several bugs and add enhancements...

STAIR: Effective Incident Response Using an End-To-End Agentic Planning Framework

Incident response planning is critical for restoring compromised software systems after cyberattacks. Common practice relies on expert-driven playbooks that encode fixed response procedures, but these static workflows struggle to adapt to evolving incident states, changing recovery objectives, an...

Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read as evidence that the score will also catch the attacks that succeed. Harmful intent is a property of the prompt...

Beyond the Quantum Promise: A Security Analysis of Classical Control in Quantum Key Distribution

Quantum Key Distribution QKD protocols provide information-theoretic security by using quantum mechanical principles. Yet QKD is fundamentally a hybrid protocol: its security depends on the correct integration of the quantum phase with classical post-processing. While ETSI and ITUT specifications...

PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents

Smart-home assistants increasingly use multimodal large language models MLLMs that perceive video and audio directly. This raises a safety question specific to the home: can the agent tell a genuine user command from ambient or externally-sourced content, television speech, on-screen text, or an...

Empirical Analysis of Evasion and Poisoning against Malware Data Drift Detection

As concept drift due to malware evolution presents challenges for malware classification, machine learning-based data drift detection tools are developed to mitigate this problem. These data drift detector tools are designed for a different purpose and built with different techniques compared to...

MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory

Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent...

A Multimodal Automatic Redteaming Evaluation Based on Atomic Jailbreak Strategy Decoupling and Combination

Multimodal Large Language Models MLLMs have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can trigger harmful outputs and pose serious safety concerns. Existing multimodal jailbreak attacks have shown the feasibility...

CWEEP: A Lexical Static Analysis Framework for CWE Early Prevention

As the hardware layer becomes a focus point for attackers, the need for improved hardware security verification techniques is more important than ever. State-of-the-art security verification techniques require significant manual effort from individuals with security expertise. Furthermore, there ...

Benign on Label, Malicious by Design: Clean-Label Dormant-To-Activated Backdoor Via Machine Unlearning with Removable Camouflage

Existing backdoor attacks often become effective immediately after backdoor implantation and may therefore be exposed before exploitation. Machine unlearning activated dormant backdoors mitigate such behavioral exposure by remaining inactive after training and becoming effective only after select...

On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems

Artificial intelligence AI systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education. While these systems offer powerful data-driven and adaptive capabilities, their complexity, rapid evolution, and dependence on dynamic data pipelines...

Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

Large language model LLM-based intrusion detection systems IDS are increasingly studied for security monitoring, yet their robustness against feasible traffic manipulation remains largely empirical. We present Traffic-Aware Randomized Smoothing TA-RS, a classifier-agnostic certified defense that...

Adversarial Prompting Framework for AI Safety Assessment

Artificial Intelligence AI, especially Generative AI GenAI, adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack APA being one of the mos...

Securing Autonomous Vehicle Systems Via Twin-Aware Federated Reinforcement Learning

Federated reinforcement learning FRL is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat...

Pachno 1.0.6 Security Assessment Toolkit

This Python-based security assessment tool performs non-destructive exposure checks against a Pachno deployment using authenticated sessions and controlled validation techniques...

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents

As LLM agents take on offensive security work, a single out-of-scope tool call can breach a client's engagement boundary, disrupt production, or void a bug-bounty finding. Unlike a fixed safety policy, the boundary that matters is declared in the user's request and must be inferred from intent...

Rosemary 1.2.0

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...

OpenSSH 10.4p1

OpenSSH is the premier connectivity tool for remote login with the SSH protocol. It encrypts all traffic to eliminate eavesdropping, connection hijacking, and other attacks. In addition, OpenSSH provides a large suite of secure tunneling capabilities, several authentication methods, and...

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environments, robotic systems, security-operation workflows, and autonomous agents that can read private data, call tools, write files, execute code, and...

FreeBSD Security Advisory - FreeBSD-SA-26:48.compat32

FreeBSD Security Advisory - The compat32 kevent handler translates a 64-bit kevent struct into a stack- declared 32-bit struct. It did not first zero the stack struct...

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy...

Veno File Manager 4.4.9 Logs Export Checker

This is a Metasploit auxiliary module used for security testing of Veno File Manager that checks whether the log export endpoint is accessible without authentication...

PYPILINE: Malicious PyPI Package Detection Via Suspicious API Knowledge and Agent Workflow

The detection of malicious PyPI packages is crucial for maintaining the security of the open source software supply chain. Existing methods, which primarily rely on rules or traditional machine learning, suffer from poor interpretability and difficulty in adapting to novel attacks. To address thi...

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System IRS framework that converts alerts from IDS, EDR, and XDR platforms into...

FreeType Automated Font Corpus Scanner

This Python framework implements a structured font-analysis pipeline for large-scale robustness testing of FreeType font parsing behavior...

Security in a Workflow: Exploring Role-Based Agentic Architectures for Vulnerability Handling

Secure software engineering in practice is a multi-stage workflow involving vulnerability analysis, remediation, and fix verification. However, current LLM-based software security approaches often focus on isolated tasks such as detection or patch generation, with limited attention to agentic...

Falco 0.44.1

Sysdig Falco is a behavioral activity monitoring agent that is open source and comes with native support for containers. Falco lets you define highly granular rules to check for activities involving file and network activity, process execution, IPC, and much more, using a flexible syntax. Falco...

VS Code Extension Persistence

This Metasploit module installs a malicious VS Code extension into the target's VS Code extensions directory. The extension executes the payload each time VS Code is launched, providing persistent code execution. Supports VS Code, VS Code Insiders, VSCodium, VS Code Server, and Cursor. Tested...

Android ADB Wireless Network Flipper Zero Recon Scanner / Service Discovery

This is a reconnaissance scanner and discovery tool for Flipper Zero to look for Android ADB wireless networks...

ClickFix HTML Static Detector

This script is a lightweight static analysis tool designed to identify HTML pages that exhibit patterns commonly associated with ClickFix-style social engineering campaigns...

ACPM Transfer Validation and Stress Testing Proof of Concept

This C program is a controlled stress-testing proof of concept designed to evaluate robustness, parameter validation, and stability of the acpmdoxfer interface under repeated high-volume calls and intentionally oversized transfer descriptors...

ECYSAP EYE: From Cyber Situational Awareness to Mission-Centric Decision Support for Enhanced Cyberspace Operations

Operational organizations increasingly require Cyber Situational Awareness CySA capabilities that go beyond isolated technical alerts, providing mission-relevant artefacts that can be embedded into heterogeneous toolchains and cyber security or cyber defense processes. ECYSAP EYE addresses this...

FreeBSD Security Advisory - FreeBSD-SA-26:35.openssl

FreeBSD Security Advisory - Multiple issues have been reported as part of this advisory with different issues affecting different OpenSSL versions and therefore different FreeBSD versions...

Exploiting Logic Asymmetry in Modern Web Application Firewalls

This research whitepaper demonstrates that even the most modern WAFs remain vulnerable to attacks exploiting logic asymmetry in HTTP protocol processing. Real-world testing on a Weaver Ecology OA system achieved a 100% bypass rate 40/40 test cases, confirming the critical severity of this...

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the...

FIFOFox: Windows Named-Pipe Security Auditor and Fuzzer

FIFOFox is a Windows named-pipe security assessment tool for identifying weak pipe permissions, pipe-squatting exposure, and named-pipe impersonation attack paths. It combines passive auditing with authorized active testing, including fuzzing and interception-style capture, to help defenders find...

MalTree: Tracing Malware Evolution from Embeddings at Scale

Malware detection remains largely reactive: machine learning models trained on known samples degrade as threats evolve. Understanding evolutionary relationships among malware families can inform proactive defense, but traditional reverse engineering can take months to years to uncover such lineag...

NLLog: Lightweight, Explainable SOC Anomaly Detection Via Log-To-Language Rewriting

System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog Natural-Language Log, a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools...

AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses

Ensuring the protection of Artificial Intelligence AI models deployed in military Command and Control C2 systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Attacks MEAs pose a significant threat, as they enable adversaries to replicate...

Learn from Your Mistakes: Tree-Like Self-Play for Secure Code LLMs

While Large Language Models LLMs excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning SFT and Reinforcement Learning RL, typically apply coarse-grained optimizati...

DMonitor 1.0.3 Outbound Connection / Port Configuration Auditor

This Python script is an outbound connection and port configuration auditor for DMonitor version 1.0.3...

Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning

The rapid proliferation of multi-cloud and SaaS platforms has transformed Identity Security Posture Management ISPM into a fundamentally cross-vendor challenge: critical misconfigurations and privilege escalation paths increasingly span multiple identity providers, infrastructure layers, and...