Blog Posts | Joshua Berkowitz

33 Articles

AI security ×

OpenAI Aardvark: Revolutionizing Software Security with AI-Powered Defense

Software vulnerabilities are growing at an unprecedented pace. Defenders must outpace attackers to protect their code, but traditional security methods are struggling to keep up. Aardvark is OpenAI’s ...

Aardvark AI security application security autonomous agents OpenAI open source security software vulnerabilities

Oct 31, 2025

0 715

How AI-Powered Phishing Attacks Are Exploiting Copilot Studio: What You Need to Know

Phishing attacks have evolved, now leveraging AI platforms to bypass traditional security measures. A recent campaign, known as CoPhish , illustrates this shift. By weaponizing Microsoft Copilot Studi...

AI security cloud security cyber attacks identity management Microsoft Copilot OAuth phishing

Oct 27, 2025

0 4026

Docker and E2B Are Shaping the Future of Trusted AI

AI agents are changing the way developers automate workflows and build applications. Their expanding capabilities, however, have amplified concerns around trust and security . As a longstanding leader...

AI security cloud sandboxes developer productivity Docker E2B MCP tool integration trusted AI

Oct 25, 2025

0 3938

Securing AI-Generated Code: Inside Project CodeGuard's Open-Source Framework

AI-driven coding tools are revolutionizing software development by accelerating code creation and boosting productivity. Yet, this rapid pace introduces significant security risks. Many AI-generated c...

AI coding AI security code vulnerabilities open source Project CodeGuard secure development software security

Oct 23, 2025

0 1441

VSCode Extension Marketplaces: Uncovering a Critical Supply Chain Risk

Most developers trust their code editor extensions, but recent research reveals a hidden danger. Sensitive secrets embedded in VSCode and Open VSX marketplaces put over 150,000 users at risk. These vu...

AI security extension security malware risk Microsoft secrets management supply chain VSCode

Oct 15, 2025

0 12947

How a Handful of Malicious Documents Can Backdoor Massive AI Models

It might seem that poisoning a huge AI model would require corrupting a substantial portion of its training data. However, groundbreaking research reveals this isn’t the case. Experts from Anthropic, ...

adversarial machine learning AI safety AI security backdoor attacks data poisoning large language models model robustness research

Oct 14, 2025

0 4158

Inside the GitHub Copilot Chat Vulnerability: What Developers Must Know

AI-powered tools like GitHub Copilot Chat are transforming how developers write and review code, but as these assistants become more integral to workflows, they introduce new security challenges. A re...

AI security code exfiltration Content Security Policy GitHub Copilot prompt injection responsible disclosure software vulnerabilities

Oct 11, 2025

0 5313

AI Is Changing the Future of Cyber Defense

Artificial intelligence is rapidly redefining the landscape of cybersecurity. Today, organizations face an urgent imperative: harness AI tools for defense before adversaries do. As advanced models lik...

AI security automated patching Claude Sonnet 4.5 cyber defense cyber resilience industry collaboration LLM benchmarks vulnerability detection

Oct 9, 2025

0 2871

CodeMender: How Google DeepMind’s AI Agent Is Reinventing Software Security

Could a world where critical software vulnerabilities are fixed automatically, allowing developers to focus on innovation rather than constant patching be closer than you think? CodeMender is Google D...

AI security automation code analysis Gemini models open source secure coding software development vulnerability patching

Oct 6, 2025

0 12188

How Azure Agentic AI Is Transforming Enterprise Automation

No longer limited to simply answering questions, agentic AI is now capable of reasoning, taking action, and collaborating with both humans and other systems. This evolution is driving a new era in ent...

agentic AI AI security Azure AI Foundry design patterns enterprise automation multi-agent systems workflow orchestration

Oct 3, 2025

0 726

Zeroday.cloud: A New Hacking Competition for Cloud and AI Security

The security of cloud and AI infrastructure is taking a leap forward with zeroday.cloud , a new hacking competition that aims to protect the open-source software forming the backbone of global technol...

AI security bug bounty cloud security hacking competition open-source responsible disclosure vulnerability research

Oct 3, 2025

0 2530

IBM Granite 4.0 Enterprise AI: Performance, Efficiency, and Trust

IBM’s Granite 4.0 models are setting a new benchmark for enterprise AI by blending exceptional efficiency with top-tier performance. The innovative hybrid Mamba/transformer architecture dramatically r...

AI benchmarks AI security enterprise AI hybrid AI IBM Granite language models Mamba architecture model efficiency

Oct 2, 2025

0 23254

Get All The Latest Research & News!

Subscribe

Our latest content

Check out what's new !

See all

Ads

Prompt Maker Image Generator

Struggling with the perfect AI image prompt? My free app helps you generate brilliant ideas and instantly creates an image to match. Go from concept to creation in two clicks!

Try It

Most Popular Articles

Check out what the hot topics are!

See all

Follow us

Get All The Latest Research & News!

Our latest content

Prompt Maker Image Generator

Most Popular Articles

Every shirt tells a story—and every story

#ClothingForACause