Attackers keep finding new ways to fool AI 2025-12-02 at 08:14 By Anamarija Pogorelec AI development keeps accelerating while the safeguards around it move on uneven ground, according to The International AI Safety Report. Security leaders are being asked to judge exposure without dependable benchmarks. Developers build layered defenses Across the AI ecosystem, developers are […]
Attackers keep finding new ways to fool AI Read More »
DeepTeam: Open-source LLM red teaming framework 2025-11-26 at 07:37 By Sinisa Markovic Security teams are pushing large language models into products faster than they can test them, which makes any new red teaming method worth paying attention to. DeepTeam is an open-source framework built to probe these systems before they reach users, and it takes
DeepTeam: Open-source LLM red teaming framework Read More »
The confidence trap holding security back 2025-11-20 at 07:37 By Anamarija Pogorelec Security leaders often feel prepared for a major cyber incident, but performance data shows a different reality. Teams continue to miss key steps during practice scenarios, and the gap between confidence and capability keeps growing. Findings from Immersive’s Cyber Workforce Benchmark Report show
The confidence trap holding security back Read More »
Protecting mobile privacy in real time with predictive adversarial defense 2025-11-14 at 09:25 By Sinisa Markovic Mobile sensors are everywhere, quietly recording how users move, tilt, or hold their phones. The same data that powers step counters and activity trackers can also expose personal details such as gender, age, or even identity. A new study
Protecting mobile privacy in real time with predictive adversarial defense Read More »
Healthcare security is broken because its systems can’t talk to each other 2025-11-13 at 09:39 By Mirko Zorz In this Help Net Security interview, Cameron Kracke, CISO at Prime Therapeutics, discusses how the healthcare ecosystem can achieve cohesive security visibility. With hospitals, clinics, telehealth, and cloud partners all in the mix, maintaining visibility remains a
Healthcare security is broken because its systems can’t talk to each other Read More »
A new way to think about zero trust for workloads 2025-11-03 at 09:10 By Mirko Zorz Static credentials have been a weak point in cloud security for years. A new paper by researchers from SentinelOne takes direct aim at that issue with a practical model for authenticating workloads without long-lived secrets. Instead of relying on
A new way to think about zero trust for workloads Read More »
Everyone’s adopting AI, few are managing the risk 2025-10-17 at 08:52 By Anamarija Pogorelec AI is spreading across enterprise risk functions, but confidence in those systems remains uneven, according to AuditBoard. More than half of organizations report implementing AI-specific tools, and many are training teams in machine learning skills. Yet, few feel prepared for the
Everyone’s adopting AI, few are managing the risk Read More »
What if your privacy tools could learn as they go? 2025-10-14 at 11:49 By Mirko Zorz A new academic study proposes a way to design privacy mechanisms that can make use of prior knowledge about how data is distributed, even when that information is incomplete. The method allows privacy guarantees to stay mathematically sound while
What if your privacy tools could learn as they go? Read More »
From theory to training: Lessons in making NICE usable 2025-10-10 at 09:02 By Mirko Zorz SMBs may not have big budgets, but they are on the receiving end of many cyberattacks. A new study from Cleveland State University looked at how these companies could train staff without getting lost in the thousands of skills and
From theory to training: Lessons in making NICE usable Read More »
Researchers develop AI system to detect scam websites in search results 2025-10-09 at 13:07 By Sinisa Markovic Scam websites tied to online shopping, pet sales, and other e-commerce schemes continue to cause millions in losses each year. Security tools can accurately detect fraudulent sites once they are found, but identifying new ones remains difficult. To
Researchers develop AI system to detect scam websites in search results Read More »
A2AS framework targets prompt injection and agentic AI security risks 2025-10-01 at 08:31 By Mirko Zorz AI systems are now deeply embedded in business operations, and this introduces new security risks that traditional controls are not built to handle. The newly released A2AS framework is designed to protect AI agents at runtime and prevent real-world
A2AS framework targets prompt injection and agentic AI security risks Read More »
CSA Unveils SaaS Security Controls Framework to Ease Complexity 2025-09-25 at 15:33 By Kevin Townsend New framework from the Cloud Security Alliance helps SaaS customers navigate the shared responsibility model with confidence. The post CSA Unveils SaaS Security Controls Framework to Ease Complexity appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
CSA Unveils SaaS Security Controls Framework to Ease Complexity Read More »
New framework sets baseline for SaaS security controls 2025-09-25 at 10:12 By Anamarija Pogorelec Managing security across dozens or even hundreds of SaaS apps has become a major headache. Each tool has its own settings, permissions, and logs, and most third-party risk processes only look at the vendor’s overall security, not the app itself. That
New framework sets baseline for SaaS security controls Read More »
Cybersecurity AI (CAI): Open-source framework for AI security 2025-09-22 at 10:29 By Anamarija Pogorelec Cybersecurity AI (CAI) is an open-source framework that helps security teams build and run AI-driven tools for offensive and defensive tasks. It’s designed for anyone working in security, including researchers, ethical hackers, IT staff, and organizations that want to use AI
Cybersecurity AI (CAI): Open-source framework for AI security Read More »
Building security that protects customers, not just auditors 2025-09-16 at 09:31 By Mirko Zorz In this Help Net Security interview, Nir Rothenberg, CISO at Rapyd, discusses global differences in payment security maturity and the lessons that can be learned from leading regions. He points out that good engineering usually leads to strong security, and cautions
Building security that protects customers, not just auditors Read More »
Can AI agents catch what your SOC misses? 2025-09-02 at 10:45 By Mirko Zorz A new research project called NetMoniAI shows how AI agents might reshape network monitoring and security. Developed by a team at Texas Tech University, the framework brings together two ideas: distributed monitoring at the edge and AI-driven analysis at the center.
Can AI agents catch what your SOC misses? Read More »
AIDEFEND: Free AI defense framework 2025-09-01 at 09:21 By Mirko Zorz AIDEFEND (Artificial Intelligence Defense Framework) is an open knowledge base dedicated to AI security, providing defensive countermeasures and best practices to help security pros safeguard AI and machine learning systems. Practicality is at the core of AIDEFEND. The framework is designed to be “highly
AIDEFEND: Free AI defense framework Read More »
KillChainGraph: Researchers test machine learning framework for mapping attacker behavior 2025-09-01 at 09:21 By Mirko Zorz A team of researchers from Frondeur Labs, DistributedApps.ai, and OWASP has developed a new machine learning framework designed to help defenders anticipate attacker behavior across the stages of the Cyber Kill Chain. The work explores how machine learning models
New framework aims to outsmart malware evasion tricks 2025-08-29 at 10:03 By Mirko Zorz Attackers have learned how to trick machine learning malware detectors with small but clever code changes, and researchers say they may finally have an answer. In a new paper, academics from Inria and the CISPA Helmholtz Center for Information Security describe
New framework aims to outsmart malware evasion tricks Read More »
What happens when penetration testing goes virtual and gets an AI coach 2025-08-19 at 09:32 By Mirko Zorz Cybersecurity training often struggles to match the complexity of threats. A new approach combining digital twins and LLMs aims to close that gap. Researchers from the University of Bari Aldo Moro propose using Cyber Digital Twins (CDTs)
What happens when penetration testing goes virtual and gets an AI coach Read More »