An Evaluation of the Semantic Understanding Capabilities of Large Language Models for Web Attack Payloads

Computer vision services delivered through Web interfaces and APIs process textual requests for image-resource acquisition, inference-task configuration, and result management, making Web attack-payload analysis relevant to their deployment security. Large language models LLMs can identify payloa...

The Security Feature Location Problem

Software security must be realized through security features such as authentication and encryption, but which features does a system implement, and where? We present security feature location: the task of relating code locations to security features, enabling developers to understand security...

Cybersecurity Is the True Frontier for Generative AI Success or Failure

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models LLMs to automate processes as "agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various...

Portswigger-lab

PortSwigger Web Security Academy Lab Notes This repository co...

Why Agentic AI Is Security's Next Blind Spot

Agentic AI is already running in production environments across many organizations today. It is executing tasks, consuming data, and taking actions — most likely without meaningful involvement from the security team. The industry conversation has largely framed this as a question of policy: allow...

Converging Zero Trust and IoT Security: A Multivocal Literature Review

The convergence of Internet of Things IoT security and Zero Trust ZT principles is a trending topic, demanding a comprehensive, multi-perspective analysis. We present the first multivocal literature review MLR on this topic, combining 68 academic and 36 industrial studies. This comprehensive revi...

The threat hunter’s gambit

Welcome to this week's edition of the Threat Source newsletter. " Study hard what interests you the most in the most undisciplined, irreverent and original manner possible." ― Richard Feynman " I had discovered that learning something, no matter how complex, wasn't hard when I had a reason to wan...

AgentWatcher: A Rule-Based Prompt Injection Monitor

Large language models LLMs and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: 1 their effectiveness degrades significantly as context length increases, and 2 they lack...

The Hidden Cost of Cybersecurity Specialization: Losing Foundational Skills

Cybersecurity has changed fast. Roles are more specialized, and tooling is more advanced. On paper, this should make organizations more secure. But in practice, many teams struggle with the same basic problems they faced years ago: unclear risk priorities, misaligned tooling decisions, and...

Highly Autonomous Cyber-Capable Agents: Anticipating Capabilities, Tactics, and Strategic Implications

This report introduces the concept of "Highly Autonomous Cyber-Capable Agents" HACCAs, AI systems capable of autonomously conducting multi-stage cyber campaigns at a level comparable to today's top criminal hacking groups or state-affiliated threat actors, and analyzes the security implications o...

FalconEYE 2.1.0

FalconEYE represents a paradigm shift in static code analysis. Instead of relying on predefined vulnerability patterns, it leverages large language models to reason about your code the same way a security expert would, understanding context, intent, and subtle security implications that tradition...

The Semantic Trap: Do Fine-Tuned LLMs Learn Vulnerability Root Cause or Just Functional Pattern?

LLMs demonstrate promising performance in software vulnerability detection after fine-tuning. However, it remains unclear whether these gains reflect a genuine understanding of vulnerability root causes or merely an exploitation of functional patterns. In this paper, we identify a critical failur...

AI Agents Vs. Human Investigators: Balancing Automation, Security, and Expertise in Cyber Forensic Analysis

In an era where cyber threats are rapidly evolving, the reliability of cyber forensic analysis has become increasingly critical for effective digital investigations and cybersecurity responses. AI agents are being adopted across digital forensic practices due to their ability to automate processe...

cve-pocs

CVE Proof of Concepts cve-pocs A collection of Proof of C...

Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?

Smart home IoT platforms such as openHAB rely on Trigger Action Condition TAC rules to automate device behavior, but the interplay among these rules can give rise to interaction threats, unintended or unsafe behaviors emerging from implicit dependencies, conflicting triggers, or overlapping...

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models

The protection of cyber Intellectual Property IP such as web content is an increasingly critical concern. The rise of large language models LLMs with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users...

Redefining Cyber Value: Why Business Impact Should Lead the Security Conversation

Security teams face growing demands with more tools, more data, and higher expectations than ever. Boards approve large security budgets, yet still ask the same question: what is the business getting in return? CISOs respond with reports on controls and vulnerability counts – but executives want ...

Learning How to Hack: Why Offensive Security Training Benefits Your Entire Security Team

Organizations across industries are experiencing significant escalations in cyberattacks, particularly targeting critical infrastructure providers and cloud-based enterprises. Verizon's recently released 2025 Data Breach Investigations Report found an 18% YoY increase in confirmed breaches, with...

GHSA-2487-9F55-2VG9 OZI-Project/ozi-publish Code Injection vulnerability

Impact Potentially untrusted data flows into PR creation logic. A malicious actor could construct a branch name that injects arbitrary code. Patches This is patched in 1.13.6 Workarounds Downgrade to 1.13.2 References Understanding the Risk of Script Injections...

An LLM-Based Self-Evolving Security Framework for 6G Space-Air-Ground Integrated Networks

Recently emerged 6G space-air-ground integrated networks SAGINs, which integrate satellites, aerial networks, and terrestrial communications, offer ubiquitous coverage for various mobile applications. However, the highly dynamic, open, and heterogeneous nature of SAGINs poses severe security...