Search papers, labs, and topics across Lattice.
Department of Electrical and Electronic Engineering, University of Cagliari, Italy
4
0
7
21
Slash malware detection labeling costs by 90% using combined active and semi-supervised learning, without sacrificing performance.
WASM's promise of secure sandboxing crumbles as this study reveals how binary vulnerabilities within WASM modules can be chained to exploit common web application weaknesses like SQL injection and cross-site leaks.
Automating the modeling of human-in-the-loop attacks on software reveals the quantifiable impact of software protections, moving beyond limited empirical studies.
LLMs can now automate and explain memory forensics, extracting more malware indicators of compromise than existing tools and making analysis accessible to non-experts.
