Tag: investigation
-
Slashdot: Serbian Student’s Android Phone Compromised By Exploit From Cellebrite
Source URL: https://it.slashdot.org/story/25/03/01/019202/serbian-students-android-phone-compromised-by-exploit-from-cellebrite?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Serbian Student’s Android Phone Compromised By Exploit From Cellebrite Feedly Summary: AI Summary and Description: Yes Summary: The report illustrates a concerning case of a zero-day exploit utilized by a surveillance vendor against a student critic of the Serbian government, highlighting the ongoing threats to information security in civil…
-
Hacker News: How to gain code execution on hundreds of millions of people and popular apps
Source URL: https://kibty.town/blog/todesktop/ Source: Hacker News Title: How to gain code execution on hundreds of millions of people and popular apps Feedly Summary: Comments AI Summary and Description: Yes Summary: The text details a security vulnerability discovered in the “todesk” application bundler, highlighting a significant exploit that allows arbitrary code execution in various applications relying…
-
News: 25 arrested in global hit against AI-generated child sexual abuse material
Source URL: https://www.europol.europa.eu/media-press/newsroom/news/25-arrested-in-global-hit-against-ai-generated-child-sexual-abuse-material Source: News Title: 25 arrested in global hit against AI-generated child sexual abuse material Feedly Summary: Most of the arrests were carried out simultaneously on 26 February 2025 during a global operation (Operation Cumberland) led by Danish law enforcement. More arrests are expected in the coming weeks, as the operation is still…
-
Schneier on Security: “Emergent Misalignment” in LLMs
Source URL: https://www.schneier.com/blog/archives/2025/02/emergent-misalignment-in-llms.html Source: Schneier on Security Title: “Emergent Misalignment” in LLMs Feedly Summary: Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model…
-
The Register: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o
Source URL: https://www.theregister.com/2025/02/27/llm_emergent_misalignment_study/ Source: The Register Title: Does terrible code drive you mad? Wait until you see what it does to OpenAI’s GPT-4o Feedly Summary: Model was fine-tuned to write vulnerable software – then suggested enslaving humanity Computer scientists have found that fine-tuning notionally safe large language models to do one thing badly can negatively…
-
The Register: Like a kid handing in hastily written homework at the last minute, Supermicro finally files its financial figures
Source URL: https://www.theregister.com/2025/02/26/supermicro_10k_filing/ Source: The Register Title: Like a kid handing in hastily written homework at the last minute, Supermicro finally files its financial figures Feedly Summary: SMCI had to come up with long-delayed report – or lose its slot on NASDAQ again It only took five or so months, but Supermicro has managed to…
-
Hacker News: DOGE will use AI to assess the responses of federal workers
Source URL: https://www.nbcnews.com/politics/doge/federal-workers-agencies-push-back-elon-musks-email-ultimatum-rcna193439 Source: Hacker News Title: DOGE will use AI to assess the responses of federal workers Feedly Summary: Comments AI Summary and Description: Yes Summary: The provided text discusses a controversial email sent by the U.S. Office of Personnel Management, orchestrated by Elon Musk, directing federal employees to report their weekly accomplishments. The…