Adversarial Threats to DeepFake Detection: A Practical Perspective

Neekhara, Paarth; Dolhansky, Brian; Bitton, Joanna; Ferrer, Cristian Canton

doi:10.1109/cvprw53098.2021.00103

Cited by 60 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Carlini et al [9] successfully evade detection against Frank et al's [5] state-of-the-art frequency-space DNN defense by flipping the lowest bit in each pixel of deepfake images. Similar efforts by Neekhara et al [10] and others corroborate this vulnerability.…”

Section: Introductionsupporting

confidence: 77%

“…In fact, recent work from Carlini and Farid [9] has shown that with as little as the ability to flip the lowest bit in each pixel, deepfake images can be attacked to evade detection by modern DNN deepfake detection classifiers (e.g., those from Frank et al [5] and Wang et al [22]). Neekhara et al [10] have also explored black-box attacks and Universal Adversarial Perturbation [28] style attacks on deepfake detection.…”

Section: Adversarial Examplesmentioning

confidence: 99%

See 1 more Smart Citation

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Hooda¹,

Mangaokar²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Detecting deepfakes is an important problem, but recent work has shown that DNN-based deepfake detectors are brittle against adversarial deepfakes, in which an adversary adds imperceptible perturbations to a deepfake to evade detection. In this work, we show that a modification to the detection strategy in which we replace a single classifier with a carefully chosen ensemble, in which input transformations for each model in the ensemble induces pairwise orthogonal gradients, can significantly improve robustness beyond the de facto solution of adversarial training. We present theoretical results to show that such orthogonal gradients can help thwart a first-order adversary by reducing the dimensionality of the input subspace in which adversarial deepfakes lie. We validate the results empirically by instantiating and evaluating a randomized version of such "orthogonal" ensembles for adversarial deepfake detection and find that these randomized ensembles exhibit significantly higher robustness as deepfake detectors compared to stateof-the-art deepfake detectors against adversarial deepfakes, even those created using strong PGD-500 attacks.

show abstract

Section: Introductionsupporting

confidence: 77%

Section: Adversarial Examplesmentioning

confidence: 99%

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Hooda¹,

Mangaokar²,

Feng³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Li et al [71] demonstrated that fake facial images generated using adversarial points on a face manifold can defeat two strong forensic classifiers. Even methods that won the Deepfake Detection Challenge (DFDC) [72] were easily bypassed in a practical attack scenario using transferable and accessible adversarial attacks [73].…”

Section: Robust Deepfake Detectionmentioning

confidence: 99%

Robust Deepfake On Unrestricted Media: Generation And Detection

Le¹,

Nguyen²,

Yamagishi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep learning have led to substantial improvements in deepfake generation, resulting in fake media with a more realistic appearance. Although deepfake media have potential application in a wide range of areas and are drawing much attention from both the academic and industrial communities, it also leads to serious social and criminal concerns. This chapter explores the evolution of and challenges in deepfake generation and detection. It also discusses possible ways to improve the robustness of deepfake detection for a wide variety of media (e.g., in-the-wild images and videos). Finally, it suggests a focus for future fake media research.

show abstract

“…Then, they propose two methods with the Lipschitz regularization (Woods et al, 2019) and deep image prior (Ulyanov et al, 2018) to improve the adversarial robustness of DeepFake detectors. Neekhara et al (2020) further study the adversarial attack-based evasion methods on the more challenging DeepFake Detection Challenge (DFDC) dataset (Dolhansky et al, 2020) and find that the input-preprocessing steps, as well as face detection methods across DeepFake detectors, make the adversarial transferability difficult. Then, they implement a high transferability attack method based on the universal adversarial perturbations to alleviate the challenges.…”

Section: Evasion Of Deepfake Detectionmentioning

confidence: 99%

“…Mirsky and Lee (2020) pivoted their survey to the DeepFake generation aspect with detailed generation DNN model charts. Neekhara et al (2020) provided a practical perspective that focuses on the adversarial threats to DeepFake detection. Verdoliva (2020) discussed the interplay between multimedia forensics and DeepFakes.…”

Section: Introductionmentioning

confidence: 99%

Countering Malicious DeepFakes: Survey, Battleground, and Horizon

Juefei-Xu¹,

Wang²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

The creation and the manipulation of facial appearance through deep generative approaches, known as DeepFake, have achieved significant progress and promoted a wide range of benign and malicious applications, e.g., visual effect assistance in movie and misinformation generation by faking famous persons. The evil side of this new technique poses another popular study, i.e., DeepFake detection aiming to identify the fake faces from the real ones. With the rapid development of the DeepFake-related studies in the community, both sides (i.e., DeepFake generation and detection) have formed the relationship of battleground, pushing the improvements of each other and inspiring new directions, e.g., the evasion of DeepFake detection. Nevertheless, the overview of such battleground and the new direction is unclear and neglected by recent surveys due to the rapid increase of related publications, limiting the in-depth understanding of the tendency and future works.To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 191 research papers carefully surveyed. We present the taxonomy of various DeepFake generation methods and the categorization of various DeepFake detection methods, and more importantly, we showcase the battleground between the two parties with detailed interactions between the adversaries (DeepFake generation) and the defenders (DeepFake detection). The battleground allows fresh perspective into the latest landscape of the DeepFake research and can provide valuable analysis towards the research challenges and opportunities as well as re-

show abstract

Adversarial Threats to DeepFake Detection: A Practical Perspective

Cited by 60 publications

References 26 publications

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Robust Deepfake On Unrestricted Media: Generation And Detection

Countering Malicious DeepFakes: Survey, Battleground, and Horizon

Contact Info

Product

Resources

About