53 matches found
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...
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...
An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding
Binary code analysis plays a pivotal role in the field of software security and is widely used in tasks such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code, reverse engineers face significant challenges in understandi...
CISA: Closing the Software Understanding Gap
CISA document to help close the gap and secure infrastructure with a deep, scalable understanding of software-controlled systems, including AI-systems...
Leverage the Power of 45k, free, Hugging Face Models with Spring AI and Ollama
This blog post is co-authored by our great contributor Thomas Vitale. Ollama now supports all GGUF models from Hugging Face , allowing access to over 45,000 community-created models through Spring AI's Ollama integration, runnable locally. We'll explore using this new feature with Spring AI. The...
23andMe data breach under joint investigation in two countries
The British and Canadian privacy authorities have announced they will undertake a joint investigation into the data breach at global genetic testing company 23andMe that was discovered in October 2023. On Friday October 6, 2023, 23andMe confirmed via a somewhat opaque blog post that cybercriminal...
Expert-Led Webinar - Uncovering Latest DDoS Tactics and Learn How to Fight Back
In today's rapidly evolving digital landscape, the threat of Distributed Denial of Service DDoS attacks looms more significant than ever. As these cyber threats grow in sophistication, understanding and countering them becomes crucial for any business seeking to protect its online presence. To...