born in 1995. PhD, associate professor. His mian research interests include physical adversarial attacks and defenses, model security evaluation, and trustworthy AI
born in 1995. PhD candidate, engineer. His main research interests include physical adversarial attacks and defenses, industrial artificial intelligence, and IIoT cyber security
born in 1998. Master, assistant engineer. His main research interest includes the audio adversarial attack
born in 2000. PhD candidate. His main research interests include physical adversarial attacks, AI attack and defense simulation, and trustworthy artificial intelligence
born in 1999. Master. His main research interests include physical adversarial attacks and defenses, and trustworthy artificial intelligence
born in 1992. PhD, associate professor. Her main research interests include open-world learning, model generalization, and trustworthy AI
born in 1974. PhD, professor of engineering, PhD supervisor. Her main research interests include software engineering and artificial intelligence
born in 1985. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include machine learning, computer vision, and multimedia information retrieval
Audio recognition has been widely applied in the typical scenarios, like auto-driving, Internet of things, and etc. In recent years, research on adversarial attacks in audio recognition has attracted extensive attention. However, most of the existing studies mainly rely on the coarse-grain audio features at the instance level, which leads to expensive generation time costs and weak universal attacking ability in real world. To address the problem, we propose a phonemic adversarial noise (PAN) generation paradigm, which exploits the audio features at the phoneme level to perform fast and universal adversarial attacks. Experiments are conducted using a variety of datasets commonly used in speech recognition tasks, such as LibriSpeech, to experimentally validate the effectiveness of the PAN proposed in this paper, its ability to generalize across datasets, its ability to migrate attacks across models, and its ability to migrate attacks across tasks, as well as further validating the effectiveness of the attack civilian-oriented Internet of things audio recognition application in the physical world devices. Extensive experiments demonstrate that the proposed PAN outperforms the comparative baselines by large margins (about 24 times speedup and 38% attacking ability improvement on average), and the sampling strategy and learning method proposed in this paper are significant in reducing the training time and improving the attack capability.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |