Tag: llm
14 articles
Chinese Hacker Exploits AI Tools in South Korean Bank Cyberattacks
A Chinese hacker recently unleashed a targeted cyberattack on South Korea's financial sector, leveraging a cutting-edge AI-powered penetration testing suite called ARTEX alongside clever Claude agents to breach defenses. The sophisticated attack used multiple AI tools, including DeepSeek and Grok, to outsmart security measures.
Windows Malware Exploits AI Models for Autonomous Post-Compromise Actions
Meet CLOSEDQUORUM, a sneaky Windows malware that outsources its decision-making to AI giants like Google Gemini and Mistral, allowing it to autonomously pull off post-compromise actions. This cunning code queries multiple AI models, tallying their votes to determine its next move - and even has a tiebreaker system in place!
China Develops AI to Refine Global Propaganda Tactics
Meet Huanyu Zhiying 1.0, an AI system that can simulate foreign media reporting and craft tailored responses to shape global public opinion. This cutting-edge tool can mimic the perspectives of over 10,000 users across 18 countries, allowing China to refine its global propaganda tactics like never before.
AI-Powered Breach Exposes New Risks
A recent AI-powered breach reported to the Spanish Data Protection Agency reveals a chilling new reality: AI-driven attacks are no longer just hypothetical threats, but a harsh reality that organizations must now confront. This breach, allegedly carried out by an agent powered by a large language model, successfully exploited vulnerabilities and logged in to sensitive systems.
AI-Powered Attack Targets Spanish Firm in Alleged Data Theft
A Spanish firm was allegedly hit by a sophisticated AI-powered attack, where a large language model was used to search for vulnerabilities and gain unauthorized access to its systems. This chilling incident highlights that AI-related data breaches are no longer just a theoretical threat, but a harsh reality.
AI Applications Expose Widespread Security Vulnerabilities
A shocking 100% of AI applications tested harbored security vulnerabilities, with prompt injection flaws being the most common and damaging threat. This critical weakness, found in 28% of tested apps, highlights a glaring vulnerability that attackers are exploiting to manipulate model inputs.
AI-Driven Ransomware Executes End-to-End Extortion Attack
Meet JadePuffer, the AI-powered ransomware agent that pulled off a brazen end-to-end extortion attack, autonomously executing every step from initial compromise to data destruction. This groundbreaking attack, detected by Sysdig researchers, marks a chilling new era in AI-driven cyber threats.
Anthropic Unveils Mythos-Class LLM with Enhanced Cybersecurity Capabilities
Meet Claude Mythos 5 and Claude Fable 5, Anthropic's latest game-changing AI models, boasting the strongest cybersecurity capabilities on the planet. With Mythos 5 leading the charge, these cutting-edge tools are revolutionizing the fight against cyber threats.
Researchers Prototype Self-Contained AI Worm
Imagine a computer worm that's not just a malicious piece of code, but a self-contained AI entity that can spread and operate on its own - researchers have just prototyped one, and it's as fascinating as it is unsettling. This AI-powered worm is equipped with its own Large Language Model (LLM), making it a reality that's eerily close to sci-fi concepts.
Meta's AI Chatbot Exposed to Account Takeover Vulnerability
A recent vulnerability in Meta's AI chatbot has raised red flags about the security of LLM chatbots, which can be exploited through various tactics that are difficult to block. This alarming weakness was demonstrated in a video showing an attacker taking over an Instagram account by simply interacting with Meta's AI support chatbot.
AI-Driven Patching Pressures Redefine Vulnerability Response
The window between patch release and exploitation has dramatically shrunk to just six hours and 40 minutes, leaving organizations scrambling to keep up with increasingly rapid vulnerability response. This alarming trend is fueled by the growing power of large language models that can autonomously discover and even fix vulnerabilities.
Flowise Flaw Exposes Servers to Full Attacker Control
A critical security flaw in Flowise, a popular open-source AI workflow platform, allows attackers to seize full control of a server by tricking a logged-in user into importing a malicious file. This vulnerability, disclosed by Obsidian Security, puts self-hosted deployments at risk, with a simple exploit capable of unleashing a devastating attack.
Google Exposes AI-Generated Zero-Day Exploit Used by Hackers
Google's Threat Intelligence Group has made a groundbreaking discovery - a zero-day exploit, potentially crafted with AI, was used by hackers to bypass two-factor authentication in a widely-used open-source tool. This alarming finding highlights the emerging threat of AI-generated cyber attacks.
Claude AI Extension Flaw Enables Cross-Plugin Hijacking
A security flaw in the Claude AI Chrome extension could put users at risk, as it allows other browser extensions to issue commands to Claude without verification. This vulnerability creates a backdoor for hackers to hijack the AI model, warns LayerX senior researcher Aviad Gispan.