A New Facial Authentication Pitfall and Remedy in Web Services

Cole, Dalton; Newman, Sara; Lin, Dan

doi:10.1109/tdsc.2021.3067794

Cited by 2 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Visible Invisible Single Multiple Non Li et al [35] x x x Li et al [35] x x Lee et al [36] x x Dumford et al [37] x x x Bhagoji et al [38] x x Zhou et al [39] x x Davaslioglu et al [40] x x Zhong et al [41] x x x x x Huai et al [42] x [49] x x x Chen et al [50] x x Tan et al [51] x x x Tang et al [52] x x Wu et al [53] x x x Barni et al [54] x x x Xiong et al [55] x x x Kwon et al [56] x x x Chen et al [57] x x x Chen et al [58] x x x He et al [26] x x x x Xue et al [59] x x x x Yao et al [60] x x x Quiring et al [61] x x x Bhalerao et al [62] x x Costales et al [63] x x Kwon et al [64] x x x Liu et al [65] x x x Rakin et al [66] x x Liu et al [67] x x x Zhou et al [68] x x Zhu et al [69] x x x Gu et al [70] x x x Guo et al [71] x x x Clements et al [72] x x x x Munoz et al [73] x x x Li et al [74] x x Li et al [75] x x x Xu et al [76] x x Venceslai et al [77] x x x Kwon et al [78] x x Cole et al [79] x x Zeng et al [80] x x Pan…”

Section: White-box Gray-box Black-box Visibility Existingmentioning

confidence: 99%

See 1 more Smart Citation

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

et al. 2022

View full text Add to dashboard Cite

Deep neural networks (DNNs) have successfully delivered cutting-edge performance in several fields. With the broader deployment of DNN models on critical applications, the security of DNNs has become an active and yet nascent area. Attacks against DNNs can have catastrophic results, according to recent studies. Poisoning attacks, including backdoor attacks and Trojan attacks, are one of the growing threats against DNNs. Having a wide-angle view of these evolving threats is essential to better understand the security issues. In this regard, creating a semantic model and a knowledge graph for poisoning attacks can reveal the relationships between attacks across intricate data to enhance the security knowledge landscape. In this paper, we propose a DNN poisoning attack ontology (DNNPAO) that would enhance knowledge sharing and enable further advancements in the field. To do so, we have performed a systematic review of the relevant literature to identify the current state. We collected 28,469 papers from the IEEE, ScienceDirect, Web of Science, and Scopus databases, and from these papers, 712 research papers were screened in a rigorous process, and 55 poisoning attacks in DNNs were identified and classified. We extracted a taxonomy of the poisoning attacks as a scheme to develop DNNPAO. Subsequently, we used DNNPAO as a framework by which to create a knowledge base. Our findings open new lines of research within the field of AI security.

show abstract

Section: White-box Gray-box Black-box Visibility Existingmentioning

confidence: 99%

“…Papers on poisoning attacks that were published in the year 2020 are [36,42,44,57,58,68,74,76,83], and there was only one paper [79] in 2021, at the time when this literature review was conducted. Lee et al [36] developed a show-and-tell model that identifies a photograph of a construction site to determine safety.…”

Section: Poisoning Attacksmentioning

confidence: 99%

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A summary of triggers for each attack is provided in Table 5 on Page 12. Huai et al [42] x x x Xue et al [30] x x x Xue et al [30] x x x Liu et al [43] x Hu et al [44] x x Lin et al [45] x x x Dai et al [46] x Zhao et al [47] x Liu et al [48] x Chen et al [49] x Tan et al [50] x x Tang et al [51] x Wu et al [52] x x Barni et al [53] x Xiong et al [54] x Kwon et al [55] x Chen et al [56] x x Chen et al [57] x x He et al [31] x x x Xue et al [58] x x x Yao et al [59] x x Quiring et al [60] x Bhalerao et al [61] x x x Costales et al [62] x x Kwon et al [63] x Liu et al [64] x x Rakin et al [65] x Liu et al [66] x x Zhou et al [67] x Zhu et al [68] x Gu et al [69] x Guo et al [70] x x x x Clements et al [71] x x Munoz et al [72] x x Li et al [73] x Li et al [74] x Xu et al [75] x x Venceslai et al [76] x Kwon et al [77] x Cole et al [78] x x x x Zeng et al [79] x x Pan [80] x x Garofalo et al…”

Section: Triggersmentioning

confidence: 99%

“…Papers on poisoning attacks that were published in the year 2020 are [36,42,43,56,57,67,73,75,82], and there was only one paper [78] in 2021, at the time when this literature review had been conducted. Lee et al [36] developed a show and tell model that identifies a photograph of a construction site to determine safety.…”

Section: Poisoning Attacksmentioning

confidence: 99%

“…To limit the number of samples required for a poisoning attack, they optimized the generation approach and confined the sample search space using abnormal event gradient information. Cole et al [78] demonstrated a data poisoning attack that needs an adversarial photo injection to enable an attacker to easily mimic the victim model of the existing facial authentication systems with no need of any knowledge from the server-side. Adversaries can compromise the victim's web accounts and log into their services.…”

Section: Poisoning Attacksmentioning

confidence: 99%

See 1 more Smart Citation

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

Altoub¹,

Alqurashi²,

Yiğitcanlar³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNN) have successfully delivered a cutting-edge performance in several fields. With the broader deployment of DNN models on critical applications, the security of DNNs becomes an active and yet nascent area. Attacks against DNNs can have catastrophic results, according to recent studies. Poisoning attacks, including backdoor and Trojan attacks, are one of the growing threats against DNNs. Having a wide-angle view of these evolving threats is essential to better understand the security issues. In this regard, creating a semantic model and a knowledge graph for poisoning attacks can reveal the relationships between attacks across intricate data to enhance the security knowledge landscape. In this paper, we propose a DNN Poisoning Attacks Ontology (DNNPAO) that would enhance knowledge sharing and enable further advancements in the field. To do so, we have performed a systematic review of the relevant literature to identify the current state. We collected 28,469 papers from IEEE, ScienceDirect, Web of Science, and Scopus databases, and from these papers, 712 research papers were screened in a rigorous process, and 55 poisoning attacks in DNNs were identified and classified. We extracted a taxonomy of the poisoning attacks as a scheme to develop DNNPAO. Subsequently, we used DNNPAO as a framework to create a knowledge base. Our findings open new lines of research within the field of AI security.

show abstract

A New Facial Authentication Pitfall and Remedy in Web Services

Cited by 2 publications

References 37 publications

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks

Contact Info

Product

Resources

About