… Coding improvements aren't new for AI models, but in the case of Mythos, Anthropic found that the model can automatically develop functional cyberattacks at a highly professional level. The company also claimed its rollout poses a severe risk to global digital infrastructure. …
… Two weeks ago, the maintainer released version 1.5.9. However, it remains unclear if the security issue has been fixed. Since February 17, HiddenLayer researchers have attempted to contact the developer multiple times over email and social media, but received no reply. …
… Mistral AI is a French artificial intelligence company founded by former researchers from Google's DeepMind and Meta, which provides open-weight large language models LLMs , both open source and proprietary. In a statement to BleepingComputer, Mistral AI confirmed that hackers compromised a codeba… …
… The company is warning that threat actors are now industrializing access to premium AI models using automated account creation, proxy relays, and account-pooling infrastructure. …
New critical Exim mailer flaw allows remote code execution By Bill Toulas May 13, 2026 04:23 PM A critical vulnerability affecting certain configurations of the Exim open-source mail transfer agent could be exploited by an unauthenticated remote attacker to execute arbitrary code. …
… Researchers at HiddenLayer, a company focused on safeguarding AI and ML models against attacks, discovered the campaign on May 7, after noticing a malicious repository named Open-OSS/privacy-filter. “The repository had typosquatted OpenAI's legitimate Privacy Filter release, copied its model card n… …
… Microsoft Threat Intelligence analyzed the payload delivered via a malicious Mistral AI package on PyPI. The actor named it 'transformers.pyz', which may be to impersonate the Hugging Face open-source Python library Transformers used for accessing pre-trained models for natural language processing. …
… File Uploads to SaaS and AI Tools: File uploads remain a major data loss vector, and one that appears like normal activity on the surface. …
… A verified data training opt-out status for each approved tool. Many AI tools use company inputs to improve their models by default unless enterprise settings are explicitly configured otherwise. …
… Download Now Related Articles: Paid AI Accounts Are Now a Hot Underground Commodity Fake OpenAI repository on Hugging Face pushes infostealer malware New stealthy Quasar Linux malware targets software developers Threat actor uses Microsoft Teams to deploy new “Snow” malware WordPress plugin suite h… …