Disguising Attacks with Explanation-Aware Backdoors.
Maximilian NoppelLukas PeterChristian WressneggerPublished in: SP (2023)
Keyphrases
- countermeasures
- watermarking scheme
- satisfiability problem
- explanation based learning
- malicious attacks
- security protocols
- chosen plaintext
- terrorist attacks
- traffic analysis
- security threats
- sat instances
- security mechanisms
- watermarking algorithm
- sat solvers
- orders of magnitude
- machine learning
- hidden structure
- generating explanations
- detect malicious
- data sets