8337 matches found
EUVD-2014-0453
Malware in sbrugna...
EUVD-2013-5666
Malware in sbrugna...
EUVD-2009-3836
Malware in sbrugna...
EUVD-2013-0449
Malware in sbrugna...
EUVD-2019-6496
Malware in sbrugna...
EUVD-2019-6495
Malware in sbrugna...
EUVD-2019-1525
Malware in sbrugna...
EUVD-2017-15230
Malware in sbrugna...
EUVD-2017-12926
Malware in sbrugna...
EUVD-2010-0141
Malware in sbrugna...
Towards Reliable and Practical LLM Security Evaluations Via Bayesian Modelling
Before adopting a new large language model LLM architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be difficult to trust, often drawing conclusions from LLMs that are not meaningfully comparable, relying on heuristic inputs or employing metrics that fai...
CVE-2025-59159 SillyTavern Web Interface Vulnerable to DNS Rebinding
SillyTavern is a locally installed user interface that allows users to interact with text generation large language models, image generation engines, and text-to-speech voice models. In versions prior to 1.13.4, the web user interface for SillyTavern is susceptible to DNS rebinding, allowing...
New Report Links Research Firms BIETA and CIII to China's MSS Cyber Operations
A Chinese company named the Beijing Institute of Electronics Technology and Application BIETA has been assessed to be likely led by the Ministry of State Security MSS. The assessment comes from evidence that at least four BIETA personnel have clear or possible links to MSS officers and their...
PT-2025-40909
Name of the Vulnerable Software and Affected Versions python-socketio versions prior to 5.14.0 Description python-socketio is a Python implementation of the Socket.IO realtime client and server. A remote code execution issue in python-socketio allows attackers to execute arbitrary Python code...
Agentic Misalignment: How LLMs Could Be Insider Threats
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only...
EUVD-2022-6414
Malicious code in bioql PyPI...
EUVD-2021-7109
Malicious code in bioql PyPI...
EUVD-2025-23790
Malicious code in bioql PyPI...