#1 Trusted Cybersecurity News Platform Followed by 4.50+ million
The Hacker News Logo
Subscribe – Get Latest News
Cloud Security

Prompt Injection | Breaking Cybersecurity News | The Hacker News

Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Mar 13, 2024 Large Language Model / AI Security
Google's  Gemini  large language model (LLM) is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks. The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Google Workspace as well as companies using the LLM API. The first vulnerability involves getting around security guardrails to leak the system prompts (or a system message), which are designed to set conversation-wide instructions to the LLM to help it generate more useful responses, by asking the model to output its "foundational instructions" in a markdown block. "A system message can be used to inform the LLM about the context," Microsoft  notes  in its documentation about LLM prompt engineering. "The context may be the type of conversation it is engaging in, or the function it is supposed to perform. It helps the LLM generate more appropriate responses.&qu
Over 100 Malicious AI/ML Models Found on Hugging Face Platform

Over 100 Malicious AI/ML Models Found on Hugging Face Platform

Mar 04, 2024 AI Security / Vulnerability
As many as 100 malicious artificial intelligence (AI)/machine learning (ML) models have been discovered in the Hugging Face platform. These include instances where loading a  pickle file  leads to code execution, software supply chain security firm JFrog said. "The model's payload grants the attacker a shell on the compromised machine, enabling them to gain full control over victims' machines through what is commonly referred to as a 'backdoor,'" senior security researcher David Cohen  said . "This silent infiltration could potentially grant access to critical internal systems and pave the way for large-scale data breaches or even corporate espionage, impacting not just individual users but potentially entire organizations across the globe, all while leaving victims utterly unaware of their compromised state." Specifically, the rogue model initiates a reverse shell connection to 210.117.212[.]93, an IP address that belongs to the Korea Research
Webinar: Learn How to Stop Hackers from Exploiting Hidden Identity Weaknesses

Webinar: Learn How to Stop Hackers from Exploiting Hidden Identity Weaknesses

Apr 10, 2024Webinar / Identity Security
We all know passwords and firewalls are important, but what about the invisible threats lurking beneath the surface of your systems? Identity Threat Exposures (ITEs) are like secret tunnels for hackers – they make your security way more vulnerable than you think. Think of it like this: misconfigurations, forgotten accounts, and old settings are like cracks in your digital fortress walls. Hackers exploit these weaknesses to steal login information, gain sneaky access, and move around your systems unnoticed, whether they're in the cloud or on-site. This upcoming webinar,  " Today's Top 4 Identity Security Threat Exposures: Are You Vulnerable? "  isn't just for tech experts—it's about protecting your business.  We'll use real-world examples and insights from Silverfort's latest report to show you the hidden dangers of ITEs. You'll learn about: The Top 4 Identity Threats You Might Be Overlooking:  We'll name them and explain why they're
Cybersecurity Resources