FISA

Microsoft has released an open access automation framework called  PyRIT  (short for Python Risk Identification Tool) to proactively identify risks in generative artificial intelligence (AI) systems. The red teaming tool is designed to "enable every organization across the globe to innovate responsibly with the latest artificial intelligence advances," Ram Shankar Siva Kumar, AI red team lead at Microsoft,  said . The company said PyRIT could be used to assess the robustness of large language model (LLM) endpoints against different harm categories such as fabrication (e.g., hallucination), misuse (e.g., bias), and prohibited content (e.g., harassment). It can also be used to identify security harms ranging from malware generation to jailbreaking, as well as privacy harms like identity theft.   PyRIT comes with five interfaces: target, datasets, scoring engine, the ability to support multiple attack strategies, and incorporating a memory component that can either take...

  A dormant package available on the Python Package Index (PyPI) repository was updated nearly after two years to propagate an information stealer malware called Nova Sentinel. The package, named  django-log-tracker , was first published to PyPI in April 2022, according to software supply chain security firm Phylum, which  detected  an anomalous update to the library on February 21, 2024. While the  linked GitHub repository  hasn't been updated since April 10, 2022, the introduction of a malicious update suggests a likely compromise of the PyPI account belonging to the developer. Django-log-tracker has been  downloaded 3,866 times  to date, with the rogue version (1.0.4) downloaded 107 times on the date it was published. The package is no longer available for download from PyPI. "In the malicious update, the attacker stripped the package of most of its original content, leaving only an __init__.py and example.py file behind," the company said. The...

Banking and logistics industries are under the onslaught of a reworked variant of a malware called  Chaes . "It has undergone major overhauls: from being rewritten entirely in Python, which resulted in lower detection rates by traditional defense systems, to a comprehensive redesign and an enhanced communication protocol," Morphisec said in a new detailed technical write-up shared with The Hacker News. Chaes, which first emerged in 2020, is known to target e-commerce customers in Latin America, particularly Brazil, to steal sensitive financial information. A subsequent analysis from Avast in early 2022 found that the threat actors behind the operation, who call themselves Lucifer, had breached more than 800 WordPress websites to deliver Chaes to users of Banco do Brasil, Loja Integrada, Mercado Bitcoin, Mercado Livre, and Mercado Pago. Further updates were detected in December 2022, when Brazilian cybersecurity company Tempest Security Intelligence uncovere...