AI Security Roundup

Daily AI security roundup covering malware, vulnerabilities, defensive research, cloud risk, and incident response signals from trusted technical sources.

ai-security EN

Master C and C++ with our new Testing Handbook chapter

We added a new chapter to our Testing Handbook: a comprehensive security checklist for C and C++ code . We’ve identified a broad range of common bug classes, known footguns, and API gotchas across C …

ai-security EN

The Hidden Security Risks of Shadow AI in Enterprises

As AI tools become more accessible, employees are adopting them without formal approval from IT and security teams. While these tools may boost productivity, automate tasks, or fill gaps in existing …

ai-security EN

Number Usage in Passwords: Take Two, (Thu, Apr 9th)

In a previous diary [1], we looked to see how numbers were used within passwords submitted to honeypots. One of the items of interest was how dates, and more specifically years, were represented …

ai-security EN

More Honeypot Fingerprinting Scans, (Wed, Apr 8th)

One question that often comes up when I talk about honeypots: Are attackers able to figure out if they are connected to a honeypot? The answer is pretty simple: Yes! Most “medium …

ai-security EN

Python Supply-Chain Compromise

Python Supply-Chain Compromise This is news : A malicious supply chain compromise has been identified in the Python Package Index package litellm version 1.82.8. The published wheel contains a …

ai-security EN

Simplifying MBA obfuscation with CoBRA

Mixed Boolean-Arithmetic (MBA) obfuscation disguises simple operations like x + y behind tangles of arithmetic and bitwise operators. Malware authors and software protectors rely on it because no …