Latest AI Security News

New AI Security Laboratory Launched to Counter Escalating Cyber Threats

Sophisticated Social Engineering Tactics Exploit AI for Financial Gain

Malicious Python Packages Exploit Popular AI Model Names

Open-Source Security Enhanced with AI-Driven Fuzz Testing

Sensitive Data Exposure and Supply Chain Vulnerabilities Top Concerns

Researchers Warn of Security Risks in Machine Learning Pipelines

AI, Cryptocurrency, and Cloaking Techniques Used to Deceive Users

Researchers Demonstrate AI-Driven Fraud Techniques

Researchers Find Critical Security Flaws in Popular AI Tools

Cybersecurity Moves to Counter AI-Powered Impersonation

AI-Powered Lovers Defraud the Vulnerable

OpenAI Report Highlights Growing AI Misuse in State-Sponsored Cyber Operations

Researchers have uncovered a method for hackers to plant "false memories" in ChatGPT

Robust Intelligence Unveils Flaw and notified OpenAI and suggested countermeasures.

Vulnerability Allowed Data Theft via Invisible Unicode Characters

Controversial AI Tool Enables Creation of Disturbing and Uncensored Images

Users Warned of AI-Generated Content Risks in Latest Agreement

New Database Highlights Potential Dangers of AI Technologies

Critical Flaws Could Allow Unauthorised Access in Healthcare Systems

Cybercriminals Adapt Strategies to Overcome Security Defenses

Navigating the Aftermath of the AI Boom

Hacker Demonstrates Vulnerability in New Screenshot Feature

AI-Generated Voice Used in Disinformation Effort

OpenAI, Meta, and TikTok Tackle AI-Powered Influence Operations

Biden's AI Initiative Gathers Momentum in Federal Agencies

Advanced Phishing Techniques Exploit AI and Cloud Services

Vulnerability Allows Arbitrary Code Execution

ChatGPT and Similar AI Services Fuel Increase in Cyber Threats

Novel Attack Exploits Prompts to Hijack AI Models

Llama Drama Vulnerability Allows Arbitrary Code Execution

AI-Generated Video Call Tricks Employee into Major Financial Loss

Misappropriated Identity on Chinese Social Media

AI-Driven Fraud Attempts to Exploit Corporate Communications

New Cyberthreat: Cybercriminals Exploit Cloud Credentials to Hijack AI Services

From Deepfakes to Jailbreaking: The Criminal Use of AI Expands

Secure AI Deployment in Intelligence

Enhancing Cyber Defenses in the Age of Sophisticated AI Systems

Facial Recognition Data Compromised Across Australian Pubs and Clubs

Innovative Diplomacy? AI to Deliver Official Statements

Enhancing Defenses Against AI Threats in Essential Sectors

AI Voice Impersonation Leads to Unauthorised Ad Campaign

Former School Staff Member Arrested for Crafting Malicious Deepfake

Precedent Set for Monitoring Indecent Image Offences with AI Restrictions

Threat actors found using AI

Army Software Chief Warns of Data Sabotage in Conflict Scenarios

Study Highlights Unintended Consequences of AI in Political Processes

Enhancing Cyber Attacks with AI: North Korea's Dangerous Leap into Advanced Phishing

Nigerian Fraud Rings Embrace AI to Enhance Online Deception

A new Generative AI model capable of generating lifelike talking faces from one image.

Convincing AI voice clones

Expanding Capabilities and Accessibility Could Raise Security Concerns

Law to Crack Down on Deepfake Sexual Exploitation

New AI Model Poses Could Cause Security Concerns Due to Accessibility and Power

Recent research reveals that OpenAI's GPT-4 can exploit real-world vulnerabilities more effectively than its predecessors and other AI models just by analysing CVE security advisories.

A United Front: Joint Efforts to Enhance AI System Security

Global Cooperation on AI Risks: Emphasizing Safety in Innovation

In-Context Learning Vulnerabilities Exposed in Popular AI Models

Thwarting AI Impersonators: A Close Call with Deepfake Technology

Emerging Threats: AI-Generated Malware Scripts Target Organisations

Critical Vulnerabilities Threaten Cloud-Based AI Platforms

Hijacked Profiles Lead to Massive Malvertising Campaign

Friend's Deception Unveils a Deepfake Nightmare

Potential Privacy Risks Prompt Congressional Ban on AI Tools

A Hidden Flaw in AI Infrastructure Unleashes Cyber Risks

Unveiling the Threats of Autonomous AI Ecosystems

Enhancing AI Systems' Security with Innovative Testing

Virtual ID Fraud Threatens Online Security Systems

Cybercriminals Harness AI to Develop Advanced Cybercrime Techniques

Urgent Call for Robust Mitigations to Tackle Emerging AI Vulnerabilities

GCHQ Director Highlights AI's Dual-Edged Impact in Security

Unified Approach to AI System Development to Enhance Security

FraudGPT, a new AI tool marketed on dark web marketplaces, is designed specifically for criminal activities

​