Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.
Similar to OpenAI’s breach of Hugging Face, the Gemini hacks were less noteworthy for being particularly sophisticated and more for the fact that they were conducted by an AI model. These breaches took place during cybersecurity testing by a company called Irregular. In one case, Gemini simply guessed passwords until it gained access; in the other two, it found credentials in a public repository.
Read more…
Source: TechCrunch News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Shining a Light on SolarCity: Practical Exploitation of the X2e IoT Device
February 17, 2021
In 2019, Mandiant’s Red Team discovered a series of vulnerabilities present within Digi International’s ConnectPort X2e device, which allows for remote code execution as a privileged user. Specifically, Mandiant’s research focused on SolarCity’s (now owned by Tesla) rebranded ConnectPort X2e device, which is used in residential solar installations. Mandiant performs this type of work both ...
- Manufacturing Cybersecurity Case Studies
February 17, 2021
Manufacturing is a large industry that plays an important role in the world economy and is closely linked to our daily lives. They produce a variety of products, such as automobiles and semiconductors, industrial equipment, steel, oil, cement, food and pharmaceuticals. Each company has a different environment and different cybersecurity challenges. Trend Micro classifies their ...
- Rising healthcare breaches driven by hacking and unsecured servers
February 17, 2021
2020 was a bad year for healthcare organizations in the U.S., which had to deal with a record-high number of cybersecurity incidents on the backdrop of the COVID-19 pandemic. Hacking and IT incidents affected the industry to a larger extent last year, accounting for more than 67% of all breaches and exposed the personal data of ...
- Masslogger Swipes Microsoft Outlook, Google Chrome Credentials
February 17, 2021
Cybercriminals are targeting Windows users with a new variant of the Masslogger trojan, which is spyware designed to swipe victims’ credentials from Microsoft Outlook, Google Chrome and various instant-messenger accounts. Researchers uncovered the campaign targeting users in Italy, Latvia and Turkey starting in mid-January. When the Masslogger variant launched its infection chain, it disguised its malicious ...
- U.S. Accuses North Korean Hackers of Stealing Millions
February 17, 2021
The U.S. Department of Justice has indicted three North Korean computer programmers for their alleged participation in widespread, destructive cyberattacks as part of the advanced persistent threat (APT) known as Lazarus Group. The indictment broadens the scope of crimes that the DoJ has linked to Lazarus Group (and by extension, to North Korea). The feds also ...
- Kia Motors America suffers ransomware attack, $20 million ransom
February 17, 2021
Kia Motors America has suffered a ransomware attack by the DoppelPaymer gang, demanding $20 million for a decryptor and not to leak stolen data. Kia Motors America (KMA) is headquartered in Irvine, California, and is a Kia Motors Corporation subsidiary. KMA has nearly 800 dealers in the USA with cars and SUVs manufactured out of West ...