Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications

Explainable Artificial Intelligence XAI has aided machine learning ML researchers with the power of scrutinizing the decisions of the black-box models. XAI methods enable looking deep inside the models' behavior, eventually generating explanations along with a perceived trust and transparency...

Family group chats: Your (very last) line of cyber defense

Welcome to this week's edition of the Threat Source newsletter, and happy Cybersecurity Awareness Month. Like everyone under the age of 35 who has at least one father, my dad sends me advice on online safety at least once a week. Does he work in information security? No. He's a recently retired...

Cybersecurity Awareness Month: Security starts with you

At Microsoft, security is our number one priority, and we believe that cybersecurity is as much about people as it is about technology. As we move into October and kick off Cybersecurity Awareness Month, this time of year really makes me think about how important online safety is—not just at work...

How Leading Security Teams Blend AI + Human Workflows (Free Webinar)

AI is changing automation—but not always for the better. That's why we're hosting a new webinar, "Workflow Clarity: Where AI Fits in Modern Automation," with Thomas Kinsella, Co-founder & Chief Customer Officer at Tines, to explore how leading teams are cutting through the hype and building...

Hitachi Energy Asset Suite (Update A)

RISK EVALUATION Successful exploitation of this vulnerability could result in the manipulation of content or the injection of data with the potential of carrying out further malicious attacks. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of...

Festo Controller CECC-S,-LK,-D Family Firmware (Update A)

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to crash services, escalate privileges, bypass authentication, or gain unauthorized access to sensitive systems and data. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize...

SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence

Effective analysis of cybersecurity and threat intelligence data demands language models that can interpret specialized terminology, complex document structures, and the interdependence of natural language and source code. Encoder-only transformer architectures provide efficient and robust...

CISA Strengthens Commitment to SLTT Governments

The Cybersecurity and Infrastructure Security Agency CISA announced that it has transitioned to a new model to better equip state, local, tribal, and territorial SLTT governments to strengthen shared responsibility nationwide. CISA is supporting our SLTT partners with access to grant funding,...

vulnerable-website

vulnerable-website This repository contains a deliberately vul...

AutoML in Cybersecurity: An Empirical Study

Automated machine learning AutoML has emerged as a promising paradigm for automating machine learning ML pipeline design, broadening AI adoption. Yet its reliability in complex domains such as cybersecurity remains underexplored. This paper systematically evaluates eight open-source AutoML...

Securing the Journey: Cybersecurity Challenges in the Tourism Industry

This weekend is World Tourism Day, a celebration of the global travel industry and the cultural, economic, and social connections it fosters. However, as the tourism industry continues to grow and evolve, it faces an increasing array of cybersecurity threats. From data breaches targeting personal...

Kicking off Cybersecurity Awareness Month 2025: Researcher spotlights and enhanced incentives

October marks Cybersecurity Awareness Month, a time when the developer community reflect on the importance of security in the evolving digital landscape. At GitHub, we understand that protecting the global software ecosystem relies on the commitment, skill, and ingenuity of the security research...

Retail at risk: How one alert uncovered a persistent cyberthreat​​

In the latest edition of our Cyberattack Series, we dive into real-world cases targeting retail organizations. With 60% of retail companies reporting operational disruptions from cyberattacks and 43% experiencing security compromises in the past year, the risks for businesses continue to increase...

Adversarial Defense in Cybersecurity: a Systematic Review of GANs for Threat Detection and Mitigation

Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks GANs act as both powerful attack enablers and promising defenses. This survey systematically reviews GAN-based adversarial defenses in cybersecurity 2021--August 31,...

Defy Security Appoints Esteemed Cybersecurity Leader Gary Warzala to Its Board of Directors

Pittsburg, United States, 23rd September 2025, CyberNewsWire...

Coherence-Driven Inference for Cybersecurity

Large language models LLMs can compile weighted graphs on natural language data to enable automatic coherence-driven inference CDI relevant to red and blue team operations in cybersecurity. This represents an early application of automatic CDI that holds near- to medium-term promise for...

Vulnlab

It is an offensive tool for learning and documentation. This rep...

CVE-2025-8531

Improper Handling of Length Parameter Inconsistency vulnerability in Mitsubishi Electric Corporation MELSEC-Q Series Q03UDVCPU, Q04UDVCPU, Q06UDVCPU, Q13UDVCPU, Q26UDVCPU, Q04UDPVCPU, Q06UDPVCPU, Q13UDPVCPU, and Q26UDPVCPU with the first 5 digits of serial No. "24082" to "27081" allows a remote...

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles

The interest in autonomous vehicles AVs for critical missions, including transportation, rescue, surveillance, reconnaissance, and mapping, is growing rapidly due to their significant safety and mobility benefits. AVs consist of complex software systems that leverage artificial intelligence AI,...

Evaluating LLM Generated Detection Rules in Cybersecurity

LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark metrics for evaluating LLM-generated cybersecurity rules. The...