ADVERSARIAL ATTACKS ON VOICE ASSISTANTS & PROTECTING AGAINST MANIPULATION
Keywords:
ASR, NLU, Security, Spoofing, Voice AssistantsAbstract
As the adoption of and engagement with Voice Assistants increase, they become increasingly attractive targets for malicious adversarial attacks by bad actors, posing a threat to the safety and privacy of authorized users. In this paper, the the end-to-end working of typical voice assistants is provided, followed by a deep dive into the top patterns of adversarial attacks via Voice Assistants. Finally, the paper also mentions the top mitigation strategies to prevent adversarial attacks and scope for future research.
References
Ashlesha Vishnu Kadam, Designing Thoughtful Experiences for Kids on Voice Assistants, International Journal of Artificial Intelligence & Machine Learning (IJAIML), 2(1), 2023, pp. 75-81. DOI: https://doi.org/10.17605/OSF.IO/HKTS8
Tawfiq Ammari, Jofish Kaye, Janice Y. Tsai, and Frank Bentley. 2019. Music, Search, and IoT: How People (Really) Use Voice Assistants. ACM Trans. Comput.-Hum. Interact. 26, 3, Article 17 (June 2019), 28 pages. https://doi.org/10.1145/3311956
Zwakman DS, Pal D, Arpnikanondt C. Usability evaluation of artificial intelligence-based voice assistants: the case of amazon Alexa. SN Comput Sci. 2021. https://doi.org/10.1007/s42979-020-00424-4.
Hoy MB. Alexa, Siri, Cortana, and more: an introduction to voice assistants. Med Ref Serv Quart. 2018;37(1):81–8.
Chen Yan, Xiaoyu Ji, Kai Wang, Qinhong Jiang, Zizhi Jin, and Wenyuan Xu. 2022. A Survey on Voice Assistant Security: Attacks and Countermeasures. ACM Comput. Surv. 55, 4, Article 84 (April 2023), 36 pages. https://doi.org/10.1145/3527153
Hadi Abdullah and Kevin Warren and Vincent Bindschaedler and Nicolas Papernot and Patrick Traynor, “SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems”, https://doi.org/10.48550/arXiv.2007.06622
Minder, B., Wolf, P., Baldauf, M. et al. Voice assistants in private households: a conceptual framework for future research in an interdisciplinary field. Humanit Soc Sci Commun 10, 173 (2023). https://doi.org/10.1057/s41599-023-01615-z
Wienrich Carolin, Reitelbach Clemens, Carolus Astrid, “The Trustworthiness of Voice Assistants in the Context of Healthcare Investigating the Effect of Perceived Expertise on the Trustworthiness of Voice Assistants, Providers, Data Receivers, and Automatic Speech Recognition”, Frontiers in Computer Science, Vol. 3, 2021. DOI: 10.3389/fcomp.2021.685250
https://www.miquido.com/blog/what-are-voice-assistants/
https://antispoofing.org/voice-antispoofing-origin-types-and-preventive-techniques/
https://www.idrnd.ai/voice-anti-spoofing/
https://www.idrnd.ai/idvoice-verified-voice-biometrics-and-anti-spoofing/
Xiaolei Liu, Xingshu Chen, Mingyong Yin, Yulong Wang, Teng Hu, Kangyi Ding, “Audio Injection Adversarial Example Attack”, https://openreview.net/pdf?id=iEkBFdmcSv
Liu, Xiaolei, Kun Wan, Yufei Ding, Xiaosong Zhang and Qingxin Zhu. “Weighted-Sampling Audio Adversarial Example Attack.” AAAI Conference on Artificial Intelligence (2019)
https://www.utsa.edu/today/2023/03/story/chen-nuit-research.html
Bolton T, Dargahi T, Belguith S, Al-Rakhami MS, Sodhro AH. On the Security and Privacy Challenges of Virtual Assistants. Sensors (Basel). 2021 Mar 26;21(7):2312. doi: 10.3390/s21072312. PMID: 33810212; PMCID: PMC8036736.
Qi-An Fu and Yinpeng Dong and Hang Su and Jun Zhu and Chao Zhang, “Automated Decision-based Iterative Adversarial Attacks”, 31st USENIX Security Symposium (USENIX Security 22), 2022
Ye Liu, Yaya Cheng, Lianli Gao, Xianglong Liu, Qilong Zhang, Jingkuan Song, “Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack”, https://openaccess.thecvf.com/content/CVPR2022/papers/Liu_Practical_Evaluation_of_Adversarial_Robustness_via_Adaptive_Auto_Attack_CVPR_2022_paper.pdf
Piotr Żelasko, Sonal Joshi, Yiwen Shao, Jesus Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur, “Adversarial Attacks and Defenses for Speech Recognition Systems”, https://arxiv.org/abs/2103.17122
Ashish Alex, Lin Wang, Paolo Gastaldo, Andrea Cavallaro, "Data augmentation for speech separation", Speech Communication, Volume 152, 2023, 102949, ISSN 0167-6393,
https://doi.org/10.1016/j.specom.2023.05.009
Muhammad Ejaz Ahmed, Il-Youp Kwak, Jun Ho Huh, Iljoo Kim, “Void: A fast and light voice liveness detection system”,
https://www.usenix.org/system/files/sec20summer_ahmed_prepub.pdf
Ali Javed, Khalid Mahmood Malik, Hafiz Malik, Aun Irtaza, "Voice spoofing detector: A unified anti-spoofing framework", Expert Systems with Applications, Volume 198, 2022, 116770, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2022.116770
Awais Khan , Khalid Mahmood Malik , James Ryan , Mikul Saravanan, “Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental analysis of generalizability, open challenges, and the way forward”, https://arxiv.org/pdf/2210.00417.pdf
Jingjin Li, Chao Chen, Lei Pan, Mostafa Rahimi Azghadi, Hossein Ghodosi, Jun Zhang, “Security and Privacy Problems in Voice Assistant Applications: A Survey”, https://arxiv.org/pdf/2304.09486.pdf
Park Joon Young, Jo Hyo Jin, Samuel Woo and Dong Hoon Lee, "BadVoice: Soundless voice-control replay attack on modern smartphones," 2016 Eighth International Conference on Ubiquitous and Future Networks (ICUFN), Vienna, Austria, 2016, pp. 882-887, doi: 10.1109/ICUFN.2016.7537163
Robert Chang, Logan Kuo, Arthur Liu, and Nader Sehatbakhsh, “SoK: A Study of the Security on Voice Processing Systems”,
https://arxiv.org/ftp/arxiv/papers/2112/2112.13144.pdf
Chen Yan, Xiaoyu Ji, Kai Wang, Qinhong Jiang, Zizhi Jin, and Wenyuan Xu. 2022. A Survey on Voice Assistant Security: Attacks and Countermeasures. ACM Comput. Surv. 55, 4, Article 84 (April 2023), 36 pages. https://doi.org/10.1145/3527153
https://thearf.org/category/ua_resource/explainable-ai-xai-helps-minimize-the-impact-of-errors/
