Search papers, labs, and topics across Lattice.
3
0
4
SHADOWPICKLE can bypass ten state-of-the-art model scanners, revealing critical vulnerabilities in the current security landscape of machine learning model hubs.
Current ML model security scanners miss nearly half of malicious models because they fail to observe runtime behavior, but a new dynamic analysis technique closes this gap.
Code LLMs fail consistency checks on 15% of inputs, revealing a significant reliability gap that existing benchmarks miss.
