Tag: protocols
-
The Register: LLM chatbots trivial to weaponise for data theft, say boffins
Source URL: https://www.theregister.com/2025/08/15/llm_chatbots_trivial_to_weaponise/ Source: The Register Title: LLM chatbots trivial to weaponise for data theft, say boffins Feedly Summary: System prompt engineering turns benign AI assistants into ‘investigator’ and ‘detective’ roles that bypass privacy guardrails A team of boffins is warning that AI chatbots built on large language models (LLM) can be tuned into malicious…
-
New York Times – Artificial Intelligence : La IA aumenta los riesgos de publicar las fotos de tus hijos en internet
Source URL: https://www.nytimes.com/es/2025/08/15/espanol/negocios/ia-riesgos-fotos-hijos-internet.html Source: New York Times – Artificial Intelligence Title: La IA aumenta los riesgos de publicar las fotos de tus hijos en internet Feedly Summary: Las aplicaciones de inteligencia artificial que generan desnudos falsos, entre otros problemas de privacidad, hacen que compartir imágenes de tus hijos sea mucho más arriesgado que hace unos…
-
The Register: Ransomware crews don’t care about your endpoint security – they’ve already killed it
Source URL: https://www.theregister.com/2025/08/14/edr_killers_ransomware/ Source: The Register Title: Ransomware crews don’t care about your endpoint security – they’ve already killed it Feedly Summary: Some custom malware, some legit software tools At least a dozen ransomware gangs have incorporated kernel-level EDR killers into their malware arsenal, allowing them to bypass almost every major endpoint security tool on…
-
Schneier on Security: LLM Coding Integrity Breach
Source URL: https://www.schneier.com/blog/archives/2025/08/llm-coding-integrity-breach.html Source: Schneier on Security Title: LLM Coding Integrity Breach Feedly Summary: Here’s an interesting story about a failure being introduced by LLM-written code. Specifically, the LLM was doing some code refactoring, and when it moved a chunk of code from one file to another it changed a “break” to a “continue.” That…
-
The Register: Stock in the Channel pulls website amid cyberattack
Source URL: https://www.theregister.com/2025/08/14/stock_in_the_channel_pulls/ Source: The Register Title: Stock in the Channel pulls website amid cyberattack Feedly Summary: Intruders accessed important systems but tells customers their data is safe A UK-based multinational that provides tech stock availability tools is telling customers that its website outage is due to a cyber attack.… AI Summary and Description: Yes…
-
Wired: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs
Source URL: https://www.wired.com/story/openai-gpt5-safety/ Source: Wired Title: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs Feedly Summary: The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent. AI Summary and Description: Yes Summary: The text discusses a new version of…
-
The Register: Secure chat darling Matrix admits pair of ‘high severity’ protocol flaws need painful fixes
Source URL: https://www.theregister.com/2025/08/13/secure_chat_darling_matrix_admits/ Source: The Register Title: Secure chat darling Matrix admits pair of ‘high severity’ protocol flaws need painful fixes Feedly Summary: Foundation warns federated servers face biggest risk, but single-instance users can take their time The maintainers of the federated secure chat protocol Matrix are warning users of a pair of “high severity…