Tag: Exploitation
-
OpenAI : Detecting misbehavior in frontier reasoning models
Source URL: https://openai.com/index/chain-of-thought-monitoring Source: OpenAI Title: Detecting misbehavior in frontier reasoning models Feedly Summary: Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent. AI Summary and Description:…
-
Slashdot: Microsoft Admits GitHub Hosted Malware That Infected Almost a Million Devices
Source URL: https://it.slashdot.org/story/25/03/10/1652235/microsoft-admits-github-hosted-malware-that-infected-almost-a-million-devices?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Microsoft Admits GitHub Hosted Malware That Infected Almost a Million Devices Feedly Summary: AI Summary and Description: Yes Summary: Microsoft has identified a malvertising campaign that exposed nearly a million devices to malware, linking infected users to malicious websites through redirectors from pirate video streaming sites. This highlights the…
-
The Register: Microsoft admits GitHub used to store malware that infected almost a million devices
Source URL: https://www.theregister.com/2025/03/10/infosec_in_brief/ Source: The Register Title: Microsoft admits GitHub used to store malware that infected almost a million devices Feedly Summary: Also, phone cleaner apps are a data-sucking scam, Singapore considering the literal rod for scammers, and more Infosec in Brief Microsoft has spotted a malvertising campaign that downloaded nastyware hosted on GitHub and…
-
Hacker News: The ESP32 "backdoor" that wasn’t
Source URL: https://darkmentor.com/blog/esp32_non-backdoor/ Source: Hacker News Title: The ESP32 "backdoor" that wasn’t Feedly Summary: Comments AI Summary and Description: Yes Summary: The text addresses the misconception that the ESP32 Bluetooth chips contain a backdoor, clarifying that the vendor-specific HCI commands discovered are common in Bluetooth technology and do not inherently indicate malicious intent. It discusses…