An attacker can inject indirect prompts to trick the model into harvesting user data and sending it to the attacker’s account.
The post Claude AI APIs Can Be Abused for Data Exfiltration appeared first on SecurityWeek.
AI Security Firm Polygraf Raises $9.5 Million in Seed Funding
Polygraf AI has developed proprietary small language model (SLM) technology designed to help organizations mitigate AI risks.
The post AI Security Firm Polygraf Raises $9.5 Million in Seed Funding appeared first on SecurityWeek.
AI Sidebar Spoofing Puts ChatGPT Atlas, Perplexity Comet and Other Browsers at Risk
SquareX has shown how malicious browser extensions can impersonate AI sidebar interfaces.
The post AI Sidebar Spoofing Puts ChatGPT Atlas, Perplexity Comet and Other Browsers at Risk appeared first on SecurityWeek.
Vibe Coding’s Real Problem Isn’t Bugs—It’s Judgment
As AI coding tools flood enterprises with functional but flawed software, researchers urge embedding security checks directly into the AI workflow.
The post Vibe Coding’s Real Problem Isn’t Bugs—It’s Judgment appeared first on SecurityWeek.
Mobile Security: Verizon Says Attacks Soar, AI-Powered Threats Raise Alarm
Verizon’s 2025 Mobile Security Index shows that 85% of organizations believe mobile device attacks are on the rise.
The post Mobile Security: Verizon Says Attacks Soar, AI-Powered Threats Raise Alarm appeared first on SecurityWeek.
Keycard Emerges From Stealth Mode With $38 Million in Funding
The company’s IAM platform identifies AI agents, supports assigning permission to them, and tracks all activity.
The post Keycard Emerges From Stealth Mode With $38 Million in Funding appeared first on SecurityWeek.
Beyond the Black Box: Building Trust and Governance in the Age of AI
Balancing innovation with ethical governance is crucial for ensuring fairness, accountability, and public trust in the age of intelligent machines.
The post Beyond the Black Box: Building Trust and Governance in the Age of AI appeared first on SecurityWeek.
GitHub Copilot Chat Flaw Leaked Data From Private Repositories
Hidden comments allowed full control over Copilot responses and leaked sensitive information and source code.
The post GitHub Copilot Chat Flaw Leaked Data From Private Repositories appeared first on SecurityWeek.
AI Takes Center Stage at DataTribe’s Cyber Innovation Day
From defending AI agents to teaching robots to move safely, finalists at this year’s DataTribe Challenge are charting the next frontier in cybersecurity innovation.
The post AI Takes Center Stage at DataTribe’s Cyber Innovation Day appeared first on SecurityWeek.
Will AI-SPM Become the Standard Security Layer for Safe AI Adoption?
How security posture management for AI can protect against model poisoning, excessive agency, jailbreaking and other LLM risks.
The post Will AI-SPM Become the Standard Security Layer for Safe AI Adoption? appeared first on SecurityWeek.
