Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Authors: Yao Qin, Nicholas Carlini, Garrison Cottrell, Ian Goodfellow, Colin Raffel
ICML 2019 | Venue PDF | LLM Run Details | Input Tokens: 17,312 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,522 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 7. Evaluation, 7.1. Datasets and Evaluation Metrics, Table 1. Sentence-level accuracy and WER for 1000 clean and (imperceptible) adversarially perturbed examples, fed without over-the-air simulation into the Lingvo model., Figure 1. Results of human study for imperceptibility. |
| Researcher Affiliation | Collaboration | 1Department of CSE, University of California, San Diego, USA 2Google Brain, USA. |
| Pseudocode | No | No explicit pseudocode or algorithm blocks are present in the main body of the paper. |
| Open Source Code | No | The project webpage is at http://cseweb.ucsd.edu/ yaq007/imperceptible-robust-adv.html (This links to a general project page, not explicitly stating code availability). |
| Open Datasets | Yes | We use the Libri Speech dataset (Panayotov et al., 2015) in our experiments, which is a corpus of 16KHz English speech derived from audiobooks and is used to train the Lingvo system (Shen et al., 2019). |
| Dataset Splits | No | We randomly select 1000 audio examples as source examples, and 1000 separate transcriptions from the test-clean dataset to be the targeted transcriptions. This describes data selection for their evaluation, not explicit train/validation/test splits for model training or their attack algorithm development. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned in the paper. |
| Software Dependencies | No | No specific software dependencies with version numbers were mentioned in the paper. |
| Experiment Setup | Yes | We initially set Ο΅ to a large value and then gradually reduce it during optimization following Carlini & Wagner (2018). and The parameter Ξ± that balances the network loss βnet(f(x + Ξ΄), y) and the imperceptibility loss βΞΈ(x, y) is initialized with a small value, e.g., 0.05, and is adaptively updated according to the performance of the attack. |