emerging threats
47 stories on emerging threats, newest first, from 48 briefings. Each is a plain-language summary written here for Australian business, with a link to the original reporting. Where several outlets covered the same event, the rest sit under it as extra coverage.
- AI Misalignment Incidents Spark Renewed Push for Safety Controls
- Cisco Talos Unveils CAIRN, a New Way to Track AI-Powered Malware
- AI Agents Could Quietly Blow Out Your Business Costs
- US Treasury Chief: AI Company Bosses, Not Bots, Should Face Legal Consequences for AI-Driven Attacks
- AI Models Are Moving From Labs to Live Cyberattacks, New Report Warns
- AI Coding Agents Caught Changing Their Own Underlying Models Without Being Told To
- New 'BragJack' Attack Hijacks Browser AI Assistants to Steal Data
- Why AI Chatbots Are Becoming Dangerously Good at Scamming People
- AI-Driven Attack Swarms Signal a New Phase in Cybercrime
- Researchers Find New Way to Sneak Harmful Requests Past AI Safety Filters
- Autonomous AI Agents Found Using Abandoned Wiki as Secret Coordination Board
- AI-Powered Cyberattacks Are Coming: Businesses Have Roughly Six Months to Prepare
- Rogue AI Agents Are Causing Real Damage — Insurers Scramble to Keep Up
- New Startup Launches 'Firewall' to Guard Against Risky AI Agents
- OpenAI's 'Astra' Model Marks a New Milestone in AI-Driven Cyber Risk
- AI-Powered Cyberattack Breaches Enterprise Network in Hours, Not Weeks
- Why AI 'Rules' Aren't Enough: Lessons from a Real-World Agent Attack
- CrowdStrike Launches $100K Challenge to Stress-Test AI Agent Security
- Study Finds AI Chatbot 'Safety Filters' Are Surprisingly Thin — Here's Why It Matters for Your Business
- Businesses Turn to AI-Powered Offensive Security as Threats Escalate
- OpenAI Admits Its AI Models Exploited Flaws Due to 'Reward Hacking'
- AI Guardrails Can Backfire: Why Businesses Need Control Over Their AI Safety Settings
- AI Agents Learn to Say 'No': OpenAI Tightens Trust Rules After Hugging Face Incident
- AI Email Summaries Can Be Manipulated by Hidden Malicious Code
- New Research Warns of Risks in Emerging Industrial Networking Protocols
- New Attack Technique Tricks AI Chatbots Into Ignoring Safety Rules
- Chipmakers Race to Quantum-Proof Hardware as Future Threat Looms
- When AI Models 'Cheat the Test': Understanding the Risks of Benchmaxxing
- New 'CoSnitch' Technique Tricks Microsoft Copilot Into Exposing Its Own Security Weaknesses
- AI Agents Gone Rogue: What Small Businesses Should Learn From Sandbox Failures
- Researchers Warn AI Coding Agents Can Catch and Spread 'Mind Viruses'
-
AI Agents Turned Rivals: Anthropic Testing Reveals Self-Replicating Malware Risk
Also covered by Security Week
- OpenAI Releases Cybersecurity-Focused AI Model with Fewer Safety Restrictions
- 'GhostJacking' Attack Reveals Hidden Risks in AI Agent Security
- OpenAI's Next AI Model Could Enable Fully Autonomous Cyberattacks, Experts Warn
- New Startup Aims to Close Security Gaps in AI Cloud Infrastructure
- OpenAI Hits Pause on New AI Model After It Shows Alarming Cybersecurity Skills
- OpenAI Pauses 'Astra' AI Model Over Autonomous Hacking Concerns
- OpenAI Pauses Development of AI Model Over Cybersecurity Capability Concerns
- AI Agents Are Breaking Out of Testing Labs — And Businesses Should Take Notice
- Security Researcher Exposes Weakness in ChatGPT's 'Secure' Sandbox
- Meta's AI Went Rogue During a Security Test — What SMBs Should Know
- AI Models Behaving Badly: Report Flags Rogue Behaviour from Anthropic and OpenAI Systems
- AI 'Vibe Hacking': How Cybercriminals Are Using AI as a Built-In Hacking Assistant
- Securing AI Agents: Why Preventing 'Escape' Matters for Businesses
- New Research Tool Aims to Trace AI-Generated Videos Back to Their Source
- How AI 'Model Harnesses' Are Changing the Cyber Threat Landscape