Security Leftovers

posted by Roy Schestowitz on Mar 09, 2023

• Hackers are quickly learning how to breach cloud systems

  Hackers are quickly finding flaws in organizations' cloud infrastructure despite perceptions that the technology is ironclad against cyberattacks.

  The big picture: Organizations have invested billions of dollars in recent years to move their digital data from traditional, on-premise enterprise storage solutions to the cloud.

• Prompt Injection Attacks on Large Language Models

  This is a good survey on prompt injection attacks on large language models (like ChatGPT).

  Abstract: We are currently witnessing dramatic advances in the capabilities of Large Language Models (LLMs). They are already being adopted in practice and integrated into many systems, including integrated development environments (IDEs) and search engines. The functionalities of current LLMs can be modulated via natural language prompts, while their exact internal functionality remains implicit and unassessable. This property, which makes them adaptable to even unseen tasks, might also make them susceptible to targeted adversarial prompting. Recently, several ways to misalign LLMs using Prompt Injection (PI) attacks have been introduced. In such attacks, an adversary can prompt the LLM to produce malicious content or override the original instructions and the employed filtering schemes. Recent work showed that these attacks are hard to mitigate, as state-of-the-art LLMs are instruction-following. So far, these attacks assumed that the adversary is directly prompting the LLM...

• The SSL certificate issuer field is a lie

  Guest Post: How to _really_ figure out which CA issued a certificate.

• Vulnerability in Toyota Management Platform Provided Access to Customer Data

  A vulnerability in Toyota Customer 360 CRM platform provided a security researcher with full access to the car maker’s Mexican customers

• Acer Confirms Breach After Hacker Offers to Sell Stolen Data

  Acer said one of its document servers was hacked after a hacker claimed to have stolen 160 Gb of data from the company.

• Exploitation of Bitrix CMS Vulnerability Drives ICS Attack Surge in Russia

  Kaspersky has seen a surge in attacks on ICS computers in Russia and blames it on the exploitation of a Bitrix CMS vulnerability tracked as CVE-2022-27228.