born in 1999. Master. His main research interests include artificial intelligence security and cloud computing security
born in 1979. PhD, professor. His main research interests include 5G security and cloud computing security
born in 1963. PhD, professor. His main research interests include information security and trusted computing
born in 1993. PhD candidate. His main research interests include deep learning, and intelligent system security testing and evaluation
born in 1987. Master candidate. His main research interests include artificial intelligence security and natural language processing
At present, adversarial attacks on speech recognition models have typically involved adding noise to the entire speech signal, resulting in a wide perturbation range and introducing high-frequency noise. Existing research has attempted to reduce the perturbation range by designing optimization targets. However, controlling the transcription result requires adding perturbations to each frame, thus limiting further reduction in perturbation range. To address this issue, we propose a novel approach that examines the feature extraction process of speech recognition systems from a frame structure perspective. The study finds that framing and windowing determine the distribution of critical regions within the frame structure. Specifically, the weight of adding perturbation to each sampling point within the frame is influenced by its location. Based on the results of perturbation analysis on input features, we partition regions with shared attributes. Then we propose the adversarial example space measurement method and evaluation index to quantify the weight of sampling points for adversarial examples generation. We conduct cross-experiments by adding perturbations at different intervals within the frame, which enables us to identify key regions for perturbation addition. Our experiments on multiple models demonstrate that adding adversarial perturbation to vital regions can narrow the perturbation range, and provide a new perspective for generating high-quality audio adversarial examples.
| 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 |