Safety tests in 2025 found that stripped-down versions of OpenAI’s models could generate detailed guidance for violent attacks, explosives and...
Vous n'êtes pas connecté
- English
- Français
- عربي
- Español
- Deutsch
- Português
- русский язык
- Català
- Italiano
- Nederlands, Vlaams
- Norsk
- فارسی
- বাংলা
- اردو
- Azərbaycan dili
- Bahasa Indonesia
- Հայերեն
- Ελληνικά
- Bosanski jezik
- українська мова
- Íslenska
- Türkmen, Түркмен
- Türkçe
- Shqip
- Eesti keel
- magyar
- Қазақ тілі
- Kalaallisut ; kalaallit oqaasii
- Lietuvių kalba
- Latviešu valoda
- македонски јазик
- Монгол
- Bahasa Melayu ; بهاس ملايو
- ဗမာစာ
- Slovenščina
- тоҷикӣ ; toğikī ; تاجیکی
- ไทย
- O'zbek ; Ўзбек ; أۇزبېك
- Tiếng Việt
- ភាសាខ្មែរ
- རྫོང་ཁ
- Soomaaliga ; af Soomaali
Rubriques :
Maroc - CYPRUSSHIPPINGNEWS.COM - A La Une - 03/Feb 03:15
Open-source AI models vulnerable to criminal misuse, researchers warn
Thousands of servers run open-source LLMs outside major AI platforms security controls, researchers say Researchers identify removed guardrails in hundreds […]
Articles similaires
Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models
itsecuritynews.info - 04/Feb 19:04
Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models (LLMs) and improve...
Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models
itsecuritynews.info - 04/Feb 19:04
Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models (LLMs) and improve...
Sam Altman warns open-source AI could enable pathogens as leaders call for global guardrails at ...
wn.com - 14:42
Big tech CEOs and...
Sam Altman warns open-source AI could enable pathogens as leaders call for global guardrails at ...
wn.com - 14:42
Big tech CEOs and...
PentestAgent – AI Penetration Testing Tool With Prebuilt Attack Playbooks and HexStrike Integration
itsecuritynews.info - 15/Feb 07:22
PentestAgent, an open-source AI agent framework from developer Masic (GH05TCREW), has introduced enhanced capabilities, including prebuilt attack...
PentestAgent – AI Penetration Testing Tool With Prebuilt Attack Playbooks and HexStrike Integration
itsecuritynews.info - 15/Feb 07:22
PentestAgent, an open-source AI agent framework from developer Masic (GH05TCREW), has introduced enhanced capabilities, including prebuilt attack...
OpenClaw Becomes New Target in Rising Wave of Supply Chain Poisoning Attacks
itsecuritynews.info - 09/Feb 08:16
OpenClaw, a rapidly growing open-source AI agent platform, faces severe supply chain risks as attackers poison its ClawHub plugin marketplace with...
AWS intruder achieved admin access in under 10 minutes thanks to AI assist, researchers say
itsecuritynews.info - 04/Feb 21:31
LLMs automated most phases of the attack A digital intruder broke into an AWS cloud environment and in just under 10 minutes went from initial access...
AWS intruder achieved admin access in under 10 minutes thanks to AI assist, researchers say
itsecuritynews.info - 04/Feb 21:31
LLMs automated most phases of the attack A digital intruder broke into an AWS cloud environment and in just under 10 minutes went from initial access...
Les derniers communiqués
-
Aucun élément