Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

How Machine Learning Transforms Security Alert Chaos into Actionable Intelligence

Learn how GitGuardian’s ML-powered risk scoring turns 10,000 noisy secrets alerts into a prioritized, actionable queue, tripling analyst efficiency, boosting critical detection 5× over rule-based systems, and safely auto-closing over a third of low-risk incidents.

Intrusion-Detection ML Pipeline: Hiring Python Data Engineers and Security Analysts

Modern cyber threats evolve rapidly, often evading traditional defenses, so organizations are adopting machine learning (ML)-driven intrusion detection systems (IDS) that learn normal network patterns and flag anomalies in real-time.

EMBER2024: Advancing the Training of Cybersecurity ML Models Against Evasive Malware

CrowdStrike data scientists are members of a team of cybersecurity researchers that recently released EMBER2024, an update to EMBER, the popular open source malware benchmark dataset originally released in 2018. The EMBER2024 dataset includes metadata, labels, and calculated features for over 3.2 million files from six different file formats.

Must-Know AI Development Services Every Startup Needs to Scale Fast

Artificial Intelligence (AI) was once a buzzword of the future, but it has now become a viable tool that contributes to innovation, efficiency, and growth. In the case of startups, AI is not the benefit; it is the requirement. The use of AI can assist startups in automating operations, customizing customer experiences, and making smarter business decisions more quickly. Within this article, we will discuss the best AI development services startups can take to stay competitive in a highly competitive market.

Introducing D-Fence: MailMarshal's Advanced Machine Learning Phishing Protection

Trustwave, A LevelBlue Company, is proud to unveil D-Fence, a powerful new machine learning-based anti-phishing layer now seamlessly integrated into MailMarshal that captures 40% more phishing emails. This capability is needed now more than ever as phishing attacks are among the top three attack vectors, according to the FBI.

CrowdStrike's Approach to Better Machine Learning Evaluation Using Strategic Data Splitting

Since day one, CrowdStrike's mission has been to stop breaches. Our pioneering AI-native approach quickly set our platform apart from the landscape of legacy cybersecurity vendors that were heavily reliant on reactive, signature-based approaches for threat detection and response. Our use of patented models across the CrowdStrike Falcon sensor and in the cloud enables us to quickly and proactively detect threats — even unknown or zero-day threats.

Machine Learning in Splunk Enterprise Security: Unleashing Hidden Detection Power

Many Splunk Enterprise Security users are benefiting from machine learning (ML) without even realizing it. Splunk Enterprise Security quietly uses ML-driven anomaly detection to spot unusual patterns or outliers in your security data that static rules or thresholds might miss.

From Chaos to Control: How ML-Driven Prioritization Solves Secrets Leaks

Security teams are still drowning in alerts. Solution? Leverage machine learning to prioritize your secrets risks! Discover how we use proprietary models that analyze the context in which your incidents occur, score their severity level, and generate clear explanations and guidelines that empower your team to focus on what matters most.

Is TensorFlow Keras "Safe Mode" Actually Safe? Bypassing safe_mode Mitigation to Achieve Arbitrary Code Execution

Update: This issue was discovered and disclosed independently to Keras by JFrog’s research team and Peng Zhou. Machine learning frameworks often rely on serialization and deserialization mechanisms to store and load models. However, improper code isolation and executable components in the models can lead to severe security risks. The structure of the Keras v3 ML Model in TensorFlow.

JFrog and Hugging Face Join Forces to Expose Malicious ML Models

ML operations, data scientists, and developers currently face critical security challenges on multiple fronts. First, staying up to date with evolving attack techniques requires constant vigilance and security know-how, which can only be achieved by a dedicated security team. Second, existing ML model scanning engines suffer from a staggering rate of false positives.