Malicious Hugging Face Models Could Trigger Remote Code Execution

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks.
Computer Weekly

Research team tricks AI chatbots into writing usable malicious code

Researchers at the University of Sheffield said they have successfully fooled a number of natural language processing (NLP) generative artificial intelligence (GenAI) tools – including ChatGPT – into ...
Security

Cybersecurity Awareness Month: How to mitigate an SQL Injection Attack

In response to this, the application security SaaS company Indusface has detailed the potential financial impact of SQL Injection attacks on businesses. Additionally, they offer best practices to help ...
techtimes

WogRAT Malware Alert: Hackers Abuse Online Notepad to Trigger Malicious Code

A newly discovered malware, dubbed 'WogRAT,' has emerged as a threat targeting both Windows and Linux operating systems. This malicious software utilizes an online notepad platform called "aNotepad" ...
CSOonline

Attackers hide malicious code in Hugging Face AI model Pickle files

The popular Python Pickle serialization format, which is common for distributing AI models, offers ways for attackers to inject malicious code that will be executed on computers when loading models ...
dbta

Addressing SAP’s SQL Injection Attacks and Directory Traversal Vulnerabilities

SAP platforms, used by 99 of the Fortune 100 companies and with over 280 million cloud subscribers worldwide, are among the most reliable business applications. As SAP administrators, your role in ...