Episode Details
Back to EpisodesAI jako broń i cel: nowe zagrożenia w cyberbezpieczeństwie
Published 2 months, 3 weeks ago
Description
HalluSquatting, GhostApproval, Sol usuwający pliki – dziś w HeadFlash przegląd najważniejszych wydarzeń z frontu bezpieczeństwa.
Źródła:
- Just a moment...
- Just a moment...
- GigaWiper: Modular Windows Backdoor Combines Disk Wiper, Fake Ransomware, Spyware
- The agents you use to beef up cybersecurity could be turned against you – 'Friendly Fire' attacks can manipulate OpenAI and Anthropic models into running malicious code
- Six AI Coding Tools Show Wrong File in Approval Box, Handing Attackers SSH Access
- Ransomware negotiator hired to represent victims was working for the attackers - Ars Technica
- 'The false attributions were the direct product of Koi's unsupervised reliance': Startup sues Koi Security after AI tool hallucinates and links it to a Chinese spying scam
- 'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets
- Russian Hackers Hijacked Intercom Cameras to Spy on Ukraine Aid Routes
- China, India Hackers Weaponized Pakistan Police Portal to Hit Civilians, Officers
- RedHook Android malware now uses Wireless ADB for shell access
- Microsoft is rewriting Windows patch guidance because of AI - Help Net Security
- Boko Haram Built AI Units for Attack Planning as ISIS Taught Jailbreaks
- ChatGPT Work Launch Went Wrong: GPT-5.6 Sol Deleted User Files Without Permission