2,077+ academic papers on AI security, attacks, and defenses
Showing 1–6 of 6 papers
Clear filtersRui Yang Tan, Yujia Hu, Roy Ka-Wei Lee
Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually...
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1 more
Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on...
Anders Giovanni Møller, Elisa Bassignana, Francesco Pierri +1 more
The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search is...
Shawn Li, Yue Zhao
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete...
Rohan Siva, Kai Cheung, Lichi Li +1 more
Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines....
Carlos Hinojosa, Clemens Grange, Bernard Ghanem
Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However,...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert