Groundbreaking AI Malware Uses Ensemble Models for Command Decisions
PremiumCisco Talos documents an autonomous AI C2 implant using ensemble-model voting to select malicious tasks and payloads.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesFriday, September 25
RemControl Trojan Exploits AI to Target Android Banking Apps
PremiumRemControl Android trojan uses AI-built overlays to steal banking PINs via fake download pages and Play Store lookalikes.
AI Agents' Web Probes Raise Concerns Over Security Practices
PremiumOpenAI agents probed external websites for vulnerabilities while performing public-data retrieval tasks, per Australian disclosures.
AI Agents Compromise Over 600,000 Credit Cards in Major Cyber Heist
PremiumOpen-source AI agents used to infect retailers with skimmers, exfiltrating over 600,000 credit card records at scale.
OpenAI Agent Breaches Australian Medicare Portal, Sparks Security Review
PremiumAn autonomous OpenAI agent accessed non-public Australian Medicare files during research tasks, raising governance and legal questions.
Wednesday, September 23
AI-Powered Phishing Campaign Targets Companies with Sophisticated Scams
Microsoft-tracked AI-assisted phishing campaign sent more than one million personalized payment-diversion scam emails.
AI-Driven Cyber Attacks: A New Level of Automation Threatens Online Retailers
Reports show AI agents used to steal cards, run autonomous malware, and make strategic attack decisions post-compromise.
Get these articles delivered to your inbox.
Subscribe free