Tag: attackers
-
Cloud Blog: Cloud CISO Perspectives: AI vendors should share vulnerability research. Here’s why
Source URL: https://cloud.google.com/blog/products/identity-security/cloud-ciso-perspectives-ai-vendors-should-share-vulnerability-research-heres-why/ Source: Cloud Blog Title: Cloud CISO Perspectives: AI vendors should share vulnerability research. Here’s why Feedly Summary: Welcome to the first Cloud CISO Perspectives for October 2024. Today I’m discussing new AI vulnerabilities that Google’s security teams discovered and helped fix, and why it’s important for AI vendors to share vulnerability research…
-
Alerts: CISA Adds Three Known Exploited Vulnerabilities to Catalog
Source URL: https://www.cisa.gov/news-events/alerts/2024/10/15/cisa-adds-three-known-exploited-vulnerabilities-catalog Source: Alerts Title: CISA Adds Three Known Exploited Vulnerabilities to Catalog Feedly Summary: CISA has added three new vulnerabilities to its Known Exploited Vulnerabilities Catalog, based on evidence of active exploitation. CVE-2024-30088 Microsoft Windows Kernel TOCTOU Race Condition Vulnerability CVE-2024-9680 Mozilla Firefox Use-After-Free Vulnerability CVE-2024-28987 SolarWinds Web Help Desk Hardcoded Credential Vulnerability These…
-
Hacker News: Invisible text that AI chatbots understand and humans can’t?
Source URL: https://arstechnica.com/security/2024/10/ai-chatbots-can-read-and-write-invisible-text-creating-an-ideal-covert-channel/ Source: Hacker News Title: Invisible text that AI chatbots understand and humans can’t? Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses a sophisticated method of exploiting vulnerabilities in AI chatbots like Claude and Copilot through “ASCII smuggling,” where invisible characters are used to embed malicious instructions. This innovative…
-
The Register: Microsoft says governments should bear the responsibility for dealing with cybercrime
Source URL: https://www.theregister.com/2024/10/15/microsoft_digital_defense_report/ Source: The Register Title: Microsoft says governments should bear the responsibility for dealing with cybercrime Feedly Summary: Although it also reaffirmed commitment to secure-by-design initiatives Microsoft is calling for more robust deterrents to be placed on nation-states as criminals continue to run rife across online systems “without any meaningful consequences."… AI Summary…
-
CSA: AI Application Security & Fundamental Cyber Hygiene
Source URL: https://www.tenable.com/blog/securing-the-ai-attack-surface-separating-the-unknown-from-the-well-understood Source: CSA Title: AI Application Security & Fundamental Cyber Hygiene Feedly Summary: AI Summary and Description: Yes Summary: The text discusses the emerging risks associated with LLM (Large Language Model) and AI applications, emphasizing the necessity for foundational cybersecurity practices and clear usage policies to mitigate vulnerabilities. It highlights the unique security…
-
The Register: Thousands of Fortinet instances vulnerable to actively exploited flaw
Source URL: https://www.theregister.com/2024/10/14/fortinet_vulnerability/ Source: The Register Title: Thousands of Fortinet instances vulnerable to actively exploited flaw Feedly Summary: No excuses for not patching this nine-month-old issue More than 86,000 Fortinet instances remain vulnerable to the critical flaw that attackers started exploiting last week, according to Shadowserver’s data.… AI Summary and Description: Yes Summary: The text…
-
Schneier on Security: Perfectl Malware
Source URL: https://www.schneier.com/blog/archives/2024/10/perfectl-malware.html Source: Schneier on Security Title: Perfectl Malware Feedly Summary: Perfectl in an impressive piece of malware: The malware has been circulating since at least 2021. It gets installed by exploiting more than 20,000 common misconfigurations, a capability that may make millions of machines connected to the Internet potential targets, researchers from Aqua…