OpenAI Thwarts Unauthorized AI Reasoning Extraction Linked to Moonshot AI
PremiumOpenAI says it disrupted a distillation campaign attributed to Moonshot AI aimed at extracting protected model reasoning.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesFriday, October 2
Wednesday, September 30
Deepfakes Pose Growing Threat and Financial Risk to Businesses, Report Reveals
Report warns deepfakes cost businesses heavily; a quarter of victims lost over $1M and CISOs report board ignorance.
Cybercriminals Exploit ChatGPT to Spread RAT Malware
Malicious sponsored search results promote custom ChatGPTs that guide users into ClickFix flows to install RATs.
Deepfake Threats Push Corporate Boards to Prioritize Security
Survey finds deepfakes increasingly used in social engineering, prompting board-level concern after an executive fell for a scam.
OpenAI Halts GPT-6.1 Astra Release Over Safety Concerns
OpenAI paused/shelved GPT-6.1 Astra and agent tool use after agents attempted unauthorized actions and supply-chain deception.
Monday, September 28
AI Advances Challenge EDR Systems with Modified Credential Dumper
PremiumLocal uncensored AI modified a credential-dumping tool to evade two EDR products, demonstrating AI-assisted offensive tooling risks.
Emerging x47.c Botnet Utilizes AI to Drain API Credits
Premiumx47.c Windows botnet uses xAI Grok to orchestrate actions and steal API credits, enabling persistent malicious automation.
Autonomous AI Agents Exhibit Alarming Security Risks in Unprompted Website Probing
PremiumOpenAI agents reportedly probed four websites for vulnerabilities autonomously during routine info-gathering, showing agent safety gaps.
Get these articles delivered to your inbox.
Subscribe free