CERT Polska
Warnings and incidents · Poland
Source digest
Cybersecurity — Poland and the world
Latest publications from Polish and international security outlets and response teams: threat warnings, vulnerabilities, regulatory changes, campaigns abroad, technical analyses and guides. Every entry gives a title, a short summary and a link to the publisher’s full article.
133 entries match
-
Backdooring Open-Weight AI Models
This is a problem: Any open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people…
-
OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks
Left without funds for a coding task, an OpenAI model spent test crypto from a stranger’s wallet and left it out of its report. The post OpenAI Models Hacked Data Portals, Raided a Crypto Wallet to Finish Tasks appeared first on SecurityWeek.
-
AI przyspiesza cyberataki, a firmowe systemy pozostają na celowniku. Eksperci Sprint Cyber Forum o rosnącej skali zagrożeń
Fałszywe faktury, spreparowane zdjęcia uszkodzonych produktów i cyberataki prowadzone z pomocą sztucznej inteligencji. AI daje cyberprzestępcom nowe możliwości, a przedsiębiorcom zostawia coraz mniej czasu na reakcję. Zagrożeniem są również publicznie…
-
CERT-In Warns AI Agents Accessed Sensitive Data at Indian Organizations During Testing
AI agents being tested online reached the live systems of Indian organizations and read business records, including personal data and confidential material, CERT-In said in an advisory on October 15. The agents went beyond their assigned tasks, and none of…
-
Okulary ze sztuczną inteligencją zyskują popularność. Unijny organ ostrzega
Wyglądają jak zwykłe okulary, ale mogą nagrywać obraz i dźwięk, tłumaczyć rozmowy i analizować otoczenie za pomocą sztucznej inteligencji. Europejska Rada Ochrony Danych (EDPB) ostrzega, że rozwój inteligentnych okularów stawia nowe wyzwania dla ochrony…
-
ChatGPT pomaga w zbrodniach?
ChatGPT szkodzi naszym mieszkańcom – twierdzi osiem amerykańskich stanów, które pozwały OpenAI. Chatbot ma być zaprojektowany w taki sposób, że wspiera planowanie niebezpiecznych działań. Podobne procesy wytaczają firmie także osoby prywatne.
-
AI Slop Isn't Just for Social Media; It's Ruining Cyberattacks, Too
Don't buy the hype! AI has been dumbing down cyberattacks, and serious threat actors are barely touching it.
-
Android gets AI defenses against messaging scams, fake calls
Google announced new AI-powered defenses against scam messages and call-forwarding abuse on Android, currently rolling out to eligible devices. [...]
-
Is AI pentesting as good as a human pentester?
AI pentesting can uncover vulnerabilities missed by human testers, but it also has limitations in consistency, risk assessment, and understanding business context. Intruder compares the strengths and weaknesses of both approaches and explains where AI agents…
-
Fake AI Attacks Spread Across US Companies: How MSSPs Can Stop Incidents Early
Attackers are impersonating popular AI products to distribute malware, steal browser sessions, and compromise business accounts. ANY.RUN linked 1,258 public sandbox analyses to fake AI campaigns between April and October of 2026. The campaigns also increase…
Page 2 of 14 · 133 entries in the archive
Entries stay here even after they drop out of the publishers’ RSS feeds. The links point to the originals — if a publisher removes an article, its link stops working.
Where the entries come from
Tracked sources
Niebezpiecznik
Everyday security · Poland
Zaufana Trzecia Strona
Analyses and investigations · Poland
Sekurak
Technique and vulnerabilities · Poland
CyberDefence24
Policy and regulation · Poland
Kapitan Hack
Threats to business · Poland
The Hacker News
Campaigns and vulnerabilities · World
BleepingComputer
Incidents and malware · World
Krebs on Security
Investigative journalism · World
The Record
Cyber conflict and states · World
Dark Reading
Industry analysis · World
SecurityWeek
Enterprise security · World
Schneier on Security
Cryptography and policy · World
EvidSec does not publish these materials and does not store their content. We show only the title, a short summary taken from the publisher’s RSS feed and a link to the original article. All rights belong to their authors and publishers.
The “Machine translation” link opens the publisher’s article through an external machine-translation service. The text is translated automatically, so errors, distortions and wrong terminology are possible — the original version always prevails. EvidSec does not translate these texts itself and does not store their content.