PT-2024-37638 · WordPress +1 · Ai Engine Wordpress Plugin +1

Name of the Vulnerable Software and Affected Versions: AI Engine versions 2.4.3 AI Engine WordPress plugin versions prior to 2.5.1 Description: The issue is related to remote-code-execution RCE via Log Poisoning. The AI Engine WordPress plugin fails to validate the file extension of logs path,...

OpenAI Blocks Iranian Influence Operation Using ChatGPT for U.S. Election Propaganda

OpenAI on Friday said it banned a set of accounts linked to what it said was an Iranian covert influence operation that leveraged ChatGPT to generate content that, among other things, focused on the upcoming U.S. presidential election. "This week we identified and took down a cluster of ChatGPT...

Unveiling Top API Vulnerabilities and Emerging Trends: Introducing the Wallarm Q2 2024 API ThreatStats™ Report

As we move through 2024, the Wallarm Research Team continues to monitor the evolving API vulnerability and threat landscape. Our latest Q2 ThreatStats™ Report reveals critical trends and developments that are reshaping the security environment. Continuing from our Q1 findings, the surge in AI API...

AI, election security headline discussions at Black Hat and DEF CON

As promised, Im back this week to recap some of the top stories coming out of Black Hat and DEF CON. Also as promised, AI was the talk of Vegas during Hacker Summer Camp or at least from what Ive been reading and hearing, I wasnt there in person. Several exhibitions and talks at both conferences...

Rogue AI is the Future of Cyber Threats

This is the first blog in a series on Rogue AI. Later articles will include technical guidance, case studies and more...

Black Hat USA 2024: Key Takeaways and Industry Trends

What a week! As Hacker Summer camp shifts into the rearview, it’s time to take a moment to reflect on the week, what we learned and the people we had the pleasure of meeting while out in Las Vegas. As is always the case at Black Hat 2024, the cybersecurity community was buzzing with the latest...

X accused of unlawfully using personal data of 60 million+ users to train its AI

In what may come as a surprise to nobody at all, theres been yet another complaint about using social media data to train Artificial Intelligence AI. This time the complaint is against X formerly Twitter and Grok, the conversational AI chatbot developed by Elon Musks company xAI. Grok is a large...

Devika 安全漏洞

Devika is an advanced AI software engineer open-sourced by stition. It can understand advanced human instructions, break them down into steps, study the relevant information, and write code to achieve a given goal. Devika suffers from a security vulnerability that stems from the presence of a...

Researchers Uncover Vulnerabilities in AI-Powered Azure Health Bot Service

Cybersecurity researchers have discovered two security flaws in Microsoft's Azure Health Bot Service that, if exploited, could permit a malicious actor to achieve lateral movement within customer environments and access sensitive patient data. The critical issues, now patched by Microsoft, could...

This Week in Spring - August 13th, 2024

Hi, Spring fans! Welcome to another installment of This Week in Spring! It's Tuesday and work is well underway to prepare for the huge SpringOne event in Las Vegas in just a few short week's time! I'm elated! So, let's get this roundup on the road so I can get back to the preparation frenzy...

D-Link G416 cfgsave Buffer Overflow Vulnerability

D-Link G416 is the AX1500 4G+ Smart Router launched by AUO in June 2025 , which supports Wi-Fi 6, AI Smart Optimization and 4G LTE Cat 6 network with up to 300Mbps internet speed. The D-Link G416 suffers from a buffer overflow vulnerability, which stems from a cfgsave stack-based buffer overflow...

AI girlfriends want to know all about you. So might ChatGPT (Lock and Code S05E17)

This week on the Lock and Code podcast… Somewhere out there is a romantic AI chatbot that wants to know everything about you. But in a revealing overlap, other AI tools—which are developed and popularized by far larger companies in technology—could crave the very same thing. For AI tools of any...

CVE-2024-7557

A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models within the same namespace. When deploying AI models, the UI provides the option to protect models with authentication. However, credentials from one model can be used to access...

How Phishing Attacks Adapt Quickly to Capitalize on Current Events

In 2023, no fewer than 94 percent of businesses were impacted by phishing attacks, a 40 percent increase compared to the previous year, according to research from Egress. What's behind the surge in phishing? One popular answer is AI – particularly generative AI, which has made it trivially easier...

The AI Hangover is Here – The End of the Beginning

After a good year of sustained exuberance, the hangover is finally here. It's a gentle one for now, as the market corrects the share price of the major players like Nvidia, Microsoft, and Google, while other players reassess the market and adjust priorities. Gartner calls it the trough of...

Taxonomy of Generative AI Misuse

Interesting paper: "Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data”: Generative, multimodal artificial intelligence GenAI offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of...

Friday Squid Blogging: SQUID Is a New Computational Tool for Analyzing Genomic AI

Yet another SQUID acronym: SQUID, short for Surrogate Quantitative Interpretability for Deepnets, is a computational tool created by Cold Spring Harbor Laboratory CSHL scientists. Its designed to help interpret how AI models analyze the genome. Compared with other analysis tools, SQUID is more...

Spring AI Embraces OpenAI's Structured Outputs: Enhancing JSON Response Reliability

OpenAI recently introduced a powerful feature called Structured Outputs, which ensures that AI-generated responses adhere strictly to a predefined JSON schema. This feature significantly improves the reliability and usability of AI-generated content in real-world applications. Today, we're excite...

CVE-2024-7557 Odh-dashboard: odh-model-controller: cross-model authentication bypass in openshift ai

A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models within the same namespace. When deploying AI models, the UI provides the option to protect models with authentication. However, credentials from one model can be used to access...

CVE-2024-7557 Odh-dashboard: odh-model-controller: cross-model authentication bypass in openshift ai

A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models within the same namespace. When deploying AI models, the UI provides the option to protect models with authentication. However, credentials from one model can be used to access...