Blue Teaming Function-Calling Agents

We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure the effectiveness of eight different defences. Our results show how these models are not safe by default, and how the...

HogVul: Black-Box Adversarial Code Generation Framework against LM-Based Vulnerability Detectors

Recent advances in software vulnerability detection have been driven by Language Model LM-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on...

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks

Large language models LLMs are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly...

DUP: Detection-Guided Unlearning for Backdoor Purification in Language Models

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full retraining or additional clean models. To address these challenges...

SoK: Securing the Final Frontier for Cybersecurity in Space-Based Infrastructure

With the advent of modern technology, critical infrastructure, communications, and national security depend increasingly on space-based assets. These assets, along with associated assets like data relay systems and ground stations, are, therefore, in serious danger of cyberattacks. Strong securit...

Evaluating the Security Efficacy of Web Application Firewalls (WAFs)

Web Application Firewalls WAFs are now a staple in defending web-facing applications and APIs, acting as specialized filters to block malicious traffic before it ever reaches your systems. But simply deploying a WAF isn’t enough, the real challenge is knowing whether it works when it matters most...

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Large Language Models LLMs are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art...

The 2025 WAF Wave from the Other Side

Forrester just published its 2025 Web application Firewall Wave. As a former industry analyst, and as a contributor on the vendor side for Imperva cough, a leader in the report, cough, let me share some reactions on the shape of this report. The Center of the Universe The first top level header H...

Imperva Security Efficacy and Operational Efficiency Leads the Industry in SecureIQLab’s Cloud WAAP Comparative Report

In the 2024 Cloud Web Application and API Protection WAAP CyberRisk Comparative Validation Report from SecureIQLab, Imperva outperformed all other vendors in both security efficacy and operational efficiency. This comprehensive report, based on third-party testing, demonstrates Imperva's commitme...

Malwarebytes wins every MRG Effitas award for 2 years in a row

ThreatDown Endpoint Protection EP achieved the highest possible score 100% and received certifications for Level 1, Exploit, Online Banking, and Ransomware in the most recent anti-malware efficacy assessment results for the Q3 2023 evaluation performed by MRG Effitas, a world leader in independen...

Malwarebytes only vendor to win every MRG Effitas award in 2022 & 2023

MRG Effitas, a world leader in independent IT research, published their anti-malware efficacy assessment results for Q1 2023. Malwarebytes Endpoint Protection EP achieved the highest possible score 100% and received certifications for Level 1, Exploit, Online Banking, and Ransomware. These result...

It’s really OK to take a break sometimes, especially in security

Welcome to this weeks edition of the Threat Source newsletter. You probably already know this by now, but May is Mental Health Awareness Month across the globe. Many people will apply this time of reflection and education to their personal lives -- its easy to discuss anxiety, depression and othe...

What Is Your Security Team Profile? Prevention, Detection, or Risk Management

Not all security teams are born equal. Each organization has a different objective. In cybersecurity, adopting a proactive approach is not just a buzzword. It actually is what makes the difference between staying behind attackers and getting ahead of them. And the solutions to do that do exist!...

Malicious code in nocuzune (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware c45c6bc0224f561bf6f25c0a0211cec4520de0b6cb103014b134a72439a28008 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Validate the Efficacy of your Endpoint Security Controls Continuously with Breach and Attack Simulations

Validate the efficacy of your Endpoint Security controls continuously with Breach and Attack Simulations By Nicolas Stricher, Trellix XDR solution Architect, EMEA and Doron RosenbergTrellix Senior Sales Engineer, Israel · March 4, 2022 Efficacy of Trellix Endpoint Security At Trellix we are proud...

2022 Planning: Metrics That Matter and Curtailing the Cobra Effect

During the British rule of India, the British government became concerned about the number of cobras in the city of Delhi. The ambitious bureaucrats came up with what they thought was the perfect solution, and they issued a bounty for cobra skins. The plan worked wonderfully at first, as cobra...

Ditch the Alert Cannon: Modernizing IDS is a Security Must-Do

After more than 20 years of underwhelming results, security leaders have accepted their intrusion detection system IDS programs as no more than a compliance checkoff. It’s no secret that IDS’s reliance on bi-modal signatures is brittle, easily evaded and often referred to as an “alert cannon.” Ti...

Designing Contact-Tracing Apps

Susan Landau wrote an essay on the privacy, efficacy, and equity of contract-tracing smartphone apps. Also see her excellent book on the topic...

6 strategies to reduce cybersecurity alert fatigue in your SOC

Today, organizations are faced with the increasingly difficult task of trying to protect their expanding digital estate from sophisticated cybersecurity threats. Migration to the cloud and a mobile workforce has dissolved the network boundary and projected the digital estate beyond its traditiona...

Forrester Study: VMware Carbon Black Cloud Provides 379% ROI

A newly published Forrester Consulting Total Economic Impact™ TEI study shows that organizations who replace their legacy endpoint security products with the VMware Carbon Black Cloud experience a 379% return on investment within three years. The commissioned study conducted on behalf of VMware...