AI Sec Watch

text-generation-webui is an open-source web interface for running Large Language Models (AI systems that generate text). Before version 4.1.1, the application allowed users to save extension settings as Python files (code files that run on servers) in the main app directory, which could let attackers overwrite important Python files like 'download-model.py' and execute malicious code when users tried to download a new model.

PartitionedDataset in kedro-datasets had a path traversal vulnerability (a security flaw where an attacker uses ".." sequences to access files outside an intended directory) that allowed attackers to write files anywhere on a system by including ".." in partition IDs (identifiers for data sections). This affected all users regardless of storage type, local or cloud-based.

Economists warn that current tools for predicting AI's impact on jobs are inadequate because they only measure "exposure" (whether AI could theoretically do a job's tasks), which doesn't account for whether employers will actually replace workers or increase productivity instead. Economist Alex Imas calls for collecting new data on how AI actually changes specific jobs and industries, since knowing a job is 28% exposed to AI tells us little about whether that job will disappear, be transformed, or become more productive.

KubeAI, a tool that runs AI models on Kubernetes (a system for managing containerized applications), has a vulnerability in versions before 0.23.2 where attackers can inject malicious shell commands (arbitrary code execution instructions) through Model resource creation. The flaw exists because the ollamaStartupProbeScript() function doesn't properly validate user input when building commands that run during startup checks.

Iran's Islamic Revolutionary Guard Corps (IRGC, a military organization) published a video threatening to destroy OpenAI's Stargate data center in Abu Dhabi if the US attacks Iran's power plants. The threat was posted to social media on April 3rd and specifically showed images of OpenAI's $30 billion facility under construction in the United Arab Emirates.

Researchers at Google DeepMind have identified a vulnerability called 'AI Agent Traps' that allows attackers to manipulate and exploit AI agents (autonomous programs that can browse the web and take actions) by hosting malicious web content designed to deceive them. This research maps out how these attacks work against AI systems that visit websites.

Healthcare workers are increasingly using AI tools on their own to handle heavy workloads, and organizations cannot stop this trend. The source emphasizes that healthcare organizations should strengthen their security practices to reduce the damage if these unsanctioned AI tools are compromised or misused.

OWASP (Open Web Application Security Project, a standards group for security best practices) has updated its generative AI security guidance to address 21 identified risks in AI systems. The update recommends that companies use separate but coordinated defense strategies tailored specifically for generative AI (AI that creates text, images, or code) and agentic AI (AI that can take actions independently).

MaliVD is a deep learning method that detects vulnerabilities (security flaws) in source code and identifies exactly which lines contain them, using a multi-modal attention mechanism (a technique that lets the AI focus on important parts of code by analyzing it in multiple ways, like looking at the code's sequence, tree structure, and relationships between components). Traditional security tools create too many false alarms and struggle with complex modern software, but MaliVD performs better than eight other detection methods by extracting different types of code features and prioritizing suspicious sections.