Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

• URL: http://arxiv.org/abs/2307.08208v1
• Date: Mon, 17 Jul 2023 02:58:25 GMT
• Title: Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
• Authors: Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Stefanos Koffas, Yiming Li
• Abstract summary: Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. In this paper, we revisit poison-only backdoor attacks against speech recognition. We exploit elements of sound ($e.g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks.
• Score: 9.24846124692153
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can implant malicious prediction behaviors into victim models by poisoning their training process. In this paper, we revisit poison-only backdoor attacks against speech recognition. We reveal that existing methods are not stealthy since their trigger patterns are perceptible to humans or machine detection. This limitation is mostly because their trigger patterns are simple noises or separable and distinctive clips. Motivated by these findings, we propose to exploit elements of sound ($e.g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks. Specifically, we insert a short-duration high-pitched signal as the trigger and increase the pitch of remaining audio clips to `mask' it for designing stealthy pitch-based triggers. We manipulate timbre features of victim audios to design the stealthy timbre-based attack and design a voiceprint selection module to facilitate the multi-backdoor attack. Our attacks can generate more `natural' poisoned samples and therefore are more stealthy. Extensive experiments are conducted on benchmark datasets, which verify the effectiveness of our attacks under different settings ($e.g.$, all-to-one, all-to-all, clean-label, physical, and multi-backdoor settings) and their stealthiness. The code for reproducing main experiments are available at \url{https://github.com/HanboCai/BadSpeech_SoE}.

Related papers

• Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition [4.164975438207411]
  In recent years, the typical backdoor attacks have been researched in speech recognition systems. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, such as pitch and timbre. To improve the stealthiness of data poisoning, we propose a non-neural and fast algorithm called Random Spectrogram Rhythm Transformation.
  arXiv  Detail & Related papers  (2024-06-16T13:29:21Z)
• Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers [51.0477382050976]
  An extra prompt token, called the switch token in this work, can turn the backdoor mode on, converting a benign model into a backdoored one. To attack a pre-trained model, our proposed attack, named SWARM, learns a trigger and prompt tokens including a switch token. Experiments on diverse visual recognition tasks confirm the success of our switchable backdoor attack, achieving 95%+ attack success rate.
  arXiv  Detail & Related papers  (2024-05-17T08:19:48Z)
• Attention-Enhancing Backdoor Attacks Against BERT-based Models [54.070555070629105]
  Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. We propose a novel Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating the attention patterns.
  arXiv  Detail & Related papers  (2023-10-23T01:24:56Z)
• Breaking Speaker Recognition with PaddingBack [18.219474338850787]
  Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. We propose PaddingBack, an inaudible backdoor attack that utilizes malicious operations to generate poisoned samples.
  arXiv  Detail & Related papers  (2023-08-08T10:36:44Z)
• Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion [14.264424889358208]
  This work explores a backdoor attack that utilizes sample-specific triggers based on voice conversion. Specifically, we adopt a pre-trained voice conversion model to generate the trigger, ensuring that the poisoned samples does not introduce any additional audible noise.
  arXiv  Detail & Related papers  (2023-06-28T02:19:31Z)
• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• BATT: Backdoor Attack with Transformation-based Triggers [72.61840273364311]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. Backdoor adversaries inject hidden backdoors that can be activated by adversary-specified trigger patterns. One recent research revealed that most of the existing attacks failed in the real physical world.
  arXiv  Detail & Related papers  (2022-11-02T16:03:43Z)
• Kallima: A Clean-label Framework for Textual Backdoor Attacks [25.332731545200808]
  We propose the first clean-label framework Kallima for synthesizing mimesis-style backdoor samples. We modify inputs belonging to the target class with adversarial perturbations, making the model rely more on the backdoor trigger.
  arXiv  Detail & Related papers  (2022-06-03T21:44:43Z)
• Rethinking the Trigger of Backdoor Attack [83.98031510668619]
  Currently, most of existing backdoor attacks adopted the setting of emphstatic trigger, $i.e.,$ triggers across the training and testing images follow the same appearance and are located in the same area. We demonstrate that such an attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
  arXiv  Detail & Related papers  (2020-04-09T17:19:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.