Friday, February 7, 2025

AI

Developers Beware! Malicious ML Models Found on Hugging Face Platform

In a concerning development for the machine learning (ML) community, researchers from ReversingLabs have uncovered malicious ML models on the Hugging Face platform, a popular hub for AI collaboration....

Hackers Exploit DeepSeek & Qwen AI Models for Malware Development

Check Point Research (CPR) has revealed that cybercriminals are increasingly leveraging the newly launched AI models, DeepSeek and Qwen, to create malicious content.These...

Splunk Introduces “DECEIVE” an AI-Powered Honeypot to Track Cyber Threats

Splunk has unveiled DECEIVE (DECeption with Evaluative Integrated Validation Engine), an innovative, AI-augmented honeypot that mimics real-world systems to lure and study cyber attackers.By leveraging advanced...

Cybercriminals Leveraging AI to Verify Stolen Credit Card Data

Cybercriminals are increasingly leveraging artificial intelligence (AI) agents to validate stolen credit card data, posing a significant threat to financial institutions and consumers.These...

Beware of Fake DeepSeek PyPI packages that Delivers Malware

The Positive Technologies Expert Security Center (PT ESC) recently uncovered a malicious campaign targeting the Python Package Index (PyPI) repository.The campaign involved two packages,...

Researchers Discover Novel Techniques to Protect AI Models from Universal Jailbreaks

In a significant advancement in AI safety, the Anthropic Safeguards Research Team has introduced a cutting-edge framework called Constitutional Classifiers to defend large language...

CryptoDNA: AI-Powered Cryptojacking Defense Against DDoS Threats in Healthcare IoT

The integration of Internet of Things (IoT) and Internet of Medical (IoM) devices has revolutionized healthcare, enabling real-time monitoring, remote diagnostics, and data-driven decision-making....

ChatGPT’s Deep Research Breakthrough Enables Faster-Than-Human Task Handling

OpenAI has introduced "Deep Research," a cutting-edge feature within ChatGPT that promises to revolutionize the way people handle complex and time-intensive tasks.Designed to synthesize...

GitHub Copilot Vulnerability Exploited to Train Malicious AI Models

GitHub Copilot, the popular AI-powered code-completion tool, has come under scrutiny after Apex Security's research unveiled two major vulnerabilities.The findings highlight weaknesses in...

Jailbreaking DeepSeek: Researchers Reveal Three New Methods to Override LLM Safety

Researchers at Palo Alto Networks' Unit 42 have revealed a troubling surge in large language model (LLM) security risks, citing three newly identified jailbreak...

Hackers Can Exploit AI Platform to Achieve Root Access via RCE Vulnerability

In a critical development within the AI industry, researchers at Noma Security have disclosed the discovery of a high-severity Remote Code Execution (RCE) vulnerability...