ReabsNet: Detecting and Revising Adversarial Examples

Chen, Jiefeng; Meng, Zihang; Sun, Changtian; Tang, Wei; Zhu, Yinglun

doi:10.48550/arxiv.1712.08250

Cited by 1 publication

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, Chen et al [28] have elaborated a detection and reforming architecture called ReabsNet. When Reabsnet receives an image x, it uses an ADM (represented by a DNN trained by adversarial training) to check whether x is legitimate or adversarial.…”

Section: Auxiliary Detection Models (Adms)mentioning

confidence: 99%

“…et al, Grosse et al, Metzen et al and Chen et al[28,62,68,127] have proposed defenses based on ADMs.Grosse et al[68] have adapted an application classifier f to also act as a ADM, training it in a dataset containing n + 1 classes. The procedure followed by the authors consists of generating adversarial images x ′ i for each legitimate image (x i , y j ) that belongs to the training set T , where i ≤ |T | × m (where m is the number of attack algorithms used) and j ≤ n. After the generation of adversarial images, it has been formed a new training set T 1 , where T 1 = T ∪{(x ′ i , n+1), i ≤ |T |×m}.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective

Machado,

Silva,

Goldschmidt

2020

Preprint

View full text Add to dashboard Cite

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works have shown those algorithms, which can even surpass the human capabilities, are vulnerable to adversarial examples. In Computer Vision, adversarial examples are images containing subtle perturbations generated by malicious optimization algorithms in order to fool classifiers. As an attempt to mitigate these vulnerabilities, numerous countermeasures have been constantly proposed in literature. Nevertheless, devising an efficient defense mechanism has proven to be a difficult task, since many approaches have already shown to be ineffective to adaptive attackers. Thus, this self-containing paper aims to provide all readerships with a review of the latest research progress on Adversarial Machine Learning in Image Classification, however with a defender's perspective. Here, novel taxonomies for categorizing adversarial attacks and defenses are introduced and discussions about the existence of adversarial examples are provided. Further, in contrast to exisiting surveys, it is also given relevant guidance that should be taken into consideration by researchers when devising and evaluating defenses. Finally, based on the reviewed literature, it is discussed some promising paths for future research.

show abstract

Section: Auxiliary Detection Models (Adms)mentioning

confidence: 99%

mentioning

confidence: 99%