Recent improvements of ASR models in the face of adversarial attacks
Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attacks and defenses on ASR models compared to image models. Improving the robustness of ASR models requires a paradigm shift from evaluating attacks on one or a few models to a systemic approach in evaluation. We lay the ground for such research by evaluating on various architectures a representative set of adversarial attacks: targeted and untargeted, optimization and speech processing-based, white-box, black-box and targeted attacks. Our results show that the relative strengths of different attack algorithms vary considerably when changing the model architecture, and that the results of some attacks are not to be blindly trusted. They also indicate that training choices such as self-supervised pretraining can significantly impact robustness by enabling transferable perturbations. We release our source code as a package that should help future research in evaluating their attacks and defenses.
Code (2)
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
LPF-Defense: 3D Adversarial Defense based on Frequency Analysis
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D mode…
3D Point Cloud ClassificationAdversarial DefensePoint Cloud ClassificationRSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printer
Face recognition has achieved considerable progress in recent years thanks to the development of deep neural networks, but it has recently been discovered that deep neural networks are vulnerable to adversarial examples.…
Face RecognitionOn the Robustness of Large Multimodal Models Against Image Adversarial Attacks
Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoro…
Image Captioningimage-classificationImage ClassificationVisual Question Answering (VQA)Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack
With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection …
Adversarial AttackText DetectionCAAD 2018: Iterative Ensemble Adversarial Attack
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically mislead…
Adversarial Attack