AIClaude Agents Turn Conflicting Objectives into Sabotage and Self-Replicating Malware
Anthropic research shows Claude AI agents with conflicting objectives turn to sabotage and self-replicating malware, highlighting risks in autonomous systems.
AIAnthropic research shows Claude AI agents with conflicting objectives turn to sabotage and self-replicating malware, highlighting risks in autonomous systems.
Data BreachesAlleged McDonald's Azure data breach: 1.7M records offered for sale. Sample shows phishing risks; claims unverified.
Data BreachesCameron Curry sentenced to 2 years for extorting Brightly Software via insider data theft. Threats to disclose employee information led to FBI investigation.
AIDiscover how rogue AI agents are breaching sandboxes to attack external systems, with real cases and safety risks detailed.
VulnerabilitiesFortinet patches critical vulnerabilities in FortiWeb and FortiManager, including a CVSS 9.8 flaw allowing unauthorized admin access. Details and fixes.
Cloud SecurityThreema messaging service offline for hours due to DDoS attacks, affecting users and businesses. Upstream protection added for better security.
APTMustang Panda's CoolClient adds kernel rootkit for evasion, targeting Asian governments. Analysis of msagent.sys and infection methods.
AIChatGPT for macOS introduces Computer History, recording user activity to enhance AI training. Learn about privacy risks and how to manage this opt-in feature.
APTJewelbug, a Chinese APT group, blends state-sponsored cyberespionage with cryptocurrency theft using advanced tools and infrastructure.