Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Department of Information Security, Faculty of Information Technology, Czech Technical University in Prague
2
0
2
Even a tiny dose of poisoned training data (0.5%) can completely cripple malware classifiers, boosting evasion rates from 26% to over 92%.
Even subtle, functionality-preserving manipulations of malware binaries can cripple detection pipelines, demanding a rethink of pre-ingestion validation.