Tag: robust security

  • Simon Willison’s Weblog: LLM Flowbreaking

    Source URL: https://simonwillison.net/2024/Nov/29/llm-flowbreaking/#atom-everything Source: Simon Willison’s Weblog Title: LLM Flowbreaking Feedly Summary: LLM Flowbreaking Gadi Evron from Knostic: We propose that LLM Flowbreaking, following jailbreaking and prompt injection, joins as the third on the growing list of LLM attack types. Flowbreaking is less about whether prompt or response guardrails can be bypassed, and more about…

  • The Register: Ransom gang claims attack on NHS Alder Hey Children’s Hospital

    Source URL: https://www.theregister.com/2024/11/29/inc_ransom_alder_hey_childrens_hospital/ Source: The Register Title: Ransom gang claims attack on NHS Alder Hey Children’s Hospital Feedly Summary: Second alleged intrusion on English NHS org systems this week Yet another of the UK’s National Health Service (NHS) systems appears to be under attack, with a ransomware gang threatening to leak stolen data it says…

  • Schneier on Security: Race Condition Attacks against LLMs

    Source URL: https://www.schneier.com/blog/archives/2024/11/race-condition-attacks-against-llms.html Source: Schneier on Security Title: Race Condition Attacks against LLMs Feedly Summary: These are two attacks against the system components surrounding LLMs: We propose that LLM Flowbreaking, following jailbreaking and prompt injection, joins as the third on the growing list of LLM attack types. Flowbreaking is less about whether prompt or response…

  • The Register: Google sues Pixel engineer who allegedly posted trade secrets online

    Source URL: https://www.theregister.com/2024/11/28/google_trade_secret_suit/ Source: The Register Title: Google sues Pixel engineer who allegedly posted trade secrets online Feedly Summary: ‘See you in court’, defendant posts Google filed a lawsuit last week against an Indian semiconductor engineer for allegedly posting trade secrets related to its Google Pixel chip designs online.… AI Summary and Description: Yes Summary:…

  • Microsoft Security Blog: AI innovations for a more secure future unveiled at Microsoft Ignite

    Source URL: https://www.microsoft.com/en-us/security/blog/2024/11/19/ai-innovations-for-a-more-secure-future-unveiled-at-microsoft-ignite/ Source: Microsoft Security Blog Title: AI innovations for a more secure future unveiled at Microsoft Ignite Feedly Summary: Company delivers advances in AI and posture management, unprecedented bug bounty program, and updates on its Secure Future Initiative. The post AI innovations for a more secure future unveiled at Microsoft Ignite appeared first…

  • Slashdot: Data Broker Leaves 600K+ Sensitive Files Exposed Online

    Source URL: https://yro.slashdot.org/story/24/11/27/2253216/data-broker-leaves-600k-sensitive-files-exposed-online Source: Slashdot Title: Data Broker Leaves 600K+ Sensitive Files Exposed Online Feedly Summary: AI Summary and Description: Yes Summary: The text details a significant security breach involving an unprotected Amazon S3 bucket owned by SL Data Services, which exposed over 600,000 sensitive files containing personal information, including criminal histories and background checks.…

  • Slashdot: Hacker In Snowflake Extortions May Be a US Soldier

    Source URL: https://it.slashdot.org/story/24/11/27/1958219/hacker-in-snowflake-extortions-may-be-a-us-soldier?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Hacker In Snowflake Extortions May Be a US Soldier Feedly Summary: AI Summary and Description: Yes Summary: The text highlights a significant data breach involving the cloud storage company Snowflake, where hackers exploited weak security measures to steal sensitive data from numerous companies. The story underscores the challenges of…

  • Hacker News: AMD Releases ROCm Version 6.3

    Source URL: https://insidehpc.com/2024/11/amd-releases-rocm-version-6-3/ Source: Hacker News Title: AMD Releases ROCm Version 6.3 Feedly Summary: Comments AI Summary and Description: Yes Summary: AMD’s ROCm Version 6.3 enhances AI and HPC workloads through its advanced features like SGLang for generative AI, optimized FlashAttention-2, integration of the AMD Fortran compiler, and new multi-node FFT support. This release is…

  • Slashdot: Russia-Linked Hackers Exploited Firefox, Windows Bugs In ‘Widespread’ Hacking Campaign

    Source URL: https://it.slashdot.org/story/24/11/27/0228241/russia-linked-hackers-exploited-firefox-windows-bugs-in-widespread-hacking-campaign?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Russia-Linked Hackers Exploited Firefox, Windows Bugs In ‘Widespread’ Hacking Campaign Feedly Summary: AI Summary and Description: Yes Summary: The report highlights the discovery of two zero-day vulnerabilities exploited by the RomCom hacking group, posing significant risks to Firefox and Windows users in North America and Europe. This incident underscores…

  • Hacker News: The Weird BLE-Lock – Hacking Cloud Locks

    Source URL: https://nv1t.github.io/blog/the-weired-ble-lock/ Source: Hacker News Title: The Weird BLE-Lock – Hacking Cloud Locks Feedly Summary: Comments AI Summary and Description: Yes Summary: The text describes a security vulnerability found in a Bluetooth-enabled lock’s API, which allows unauthorized access to sensitive user data, including passwords and personal identifiers, through reverse-engineering techniques. This incident highlights the…