Deepfake-Image Anti-Forensics with Adversarial Examples Attacks

Fan, Li; Li, Wei; Cui, Xiaohui

doi:10.3390/fi13110288

Cited by 7 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A successful adversarial attack requires embedding imperceptible noise perturbations into the fake sample, which deceives the detector into classifying the image as "real". Several classic adversarial attack methods, including Fast Gradient Sign Method (FGSM) [45], iterative FGSM [46], Carlini and Wagner l 2 -norm Attack [47], DeepFool [48] and Projected Gradient Descent (PGD) [49], are explored to expose the vulnerability of DeepFake detectors in both white-and blackbox scenarios [3]- [7], [14], [15]. Liao et al [8] improved on the efficiency of these attacks by adding perturbations to key regions of the DeepFakes instead of across the entire image.…”

Section: Anti-forensics For Deepfakesmentioning

confidence: 99%

“…• Blurring: images are blurred with a Gaussian filter with a kernel size randomly sampled from (3,5,7,9).…”

Section: Victim Detector's Capabilitymentioning

confidence: 99%

“…L adv (G, D1, D2, D3) = L(G, D1) + L(G, D2) + L(G, D3), (6) where (7) The input x varies for different discriminator, i.e., x = I for D 1 , x = I for D 2 and x = I for D 3 . Since different traces are deemed as equally significant, no additional weights are applied to each sub-item of L adv .…”

Section: Loss Functionsmentioning

confidence: 99%

See 2 more Smart Citations

Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack

Liu¹,

Chen²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

DeepFakes are raising significant social concerns. Although various DeepFake detectors have been developed as forensic countermeasures, these detectors are still vulnerable to attacks. Recently, a few attacks, principally adversarial attacks, have succeeded in cloaking DeepFake images to evade detection. However, these attacks have typical detector-specific designs, which require prior knowledge about the detector, leading to poor transferability. Moreover, these attacks only consider simple security scenarios. Less is known about how effective they are in high-level scenarios where either the detector's defensive capability or the attacker's knowledge varies. In this paper, we aim to solve the above challenges with presenting a novel attack pattern for DeepFake anti-forensics, namely, the trace removal attack. Instead of investigating the detector side, this trace removal attack looks into the original DeepFake creation pipeline, attempting to remove all detectable natural DeepFake traces to render the fake images more "authentic". This detector-agnostic design benefits the attack to be effective against arbitrary or even unknown detectors. To implement this attack, first, we perform an in-depth DeepFake trace discovery, which identifies three discernible traces: spatial anomalies, spectral disparities, and noise fingerprints. Then a trace removal network (TR-Net) is proposed based on an adversarial learning framework involving one generator and multiple discriminators. Each discriminator is responsible for one individual trace representation to avoid cross-trace interference. These multiple discriminators are arranged in parallel, which prompts the generator to remove various traces simultaneously. To evaluate the efficacy of the attack, we crafted heterogeneous security scenarios where the detectors were embedded with different levels of defense and the attackers' background knowledge of data varies. The experimental results show that the proposed attack can significantly compromise the detection accuracy of six state-of-the-art DeepFake detectors while causing only a negligible loss in visual quality to the original DeepFake samples.

show abstract

Section: Anti-forensics For Deepfakesmentioning

confidence: 99%

“…• Blurring: images are blurred with a Gaussian filter with a kernel size randomly sampled from (3,5,7,9).…”

Section: Victim Detector's Capabilitymentioning

confidence: 99%

See 1 more Smart Citation

Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack

Liu¹,

Chen²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Ding et al [47][48][49][50][51]53] propose anti-forensic tools and methods by which to bypass "DeepFake" detection on videos. On the other hand, Zhao, X et al [52,54] apply it to "DeepFake" detection in GAN-generated images.…”

mentioning

confidence: 99%

“…Studies [47][48][49][50][51][52][53][54] propose different strategies and models for generating DeepFakes that can evade forensic detection. Paper [47] propose GAN models with additional features and loss functions designed to improve visual quality and model efficiency.…”

mentioning

confidence: 99%

Systematic Review: Anti-Forensic Computer Techniques

González Arias,

Bermejo Higuera,

Rainer Granados

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The main purpose of anti-forensic computer techniques, in the broadest sense, is to hinder the investigation of a computer attack by eliminating traces and preventing the collection of data contained in a computer system. Nowadays, cyber-attacks are becoming more and more frequent and sophisticated, so it is necessary to understand the techniques used by hackers to be able to carry out a correct forensic analysis leading to the identification of the perpetrators. Despite its importance, this is a poorly represented area in the scientific literature. The disparity of the existing works, together with the small number of articles, makes it challenging to find one’s way around the vast world of computer forensics. This article presents a comprehensive review of the existing scientific literature on anti-forensic techniques, mainly DFIR (digital forensics incident response), organizing the studies according to their subject matter and orientation. It also presents key ideas that contribute to the understanding of this field of forensic science and details the shortcomings identified after reviewing the state of the art.

show abstract

Engaging with deepfakes: a meta-synthesis from the perspective of social shaping of technology theory

Vasist

Krishnan²

2022

INTR

View full text Add to dashboard Cite

PurposeThis study aims to establish a comprehensive understanding of the intricacies of how individuals engage with deepfakes, focusing on limiting adverse effects and capitalizing on their benefits.Design/methodology/approachThis study conducted a meta-synthesis of qualitative studies on deepfakes, incorporating study-specific analysis followed by a cross-study synthesis.FindingsBased on the meta-synthesis, the study developed an integrated conceptual framework based on the perspectives from the social shaping of technology theory embedding deepfake-related assertions, motivations, the subtleties of digital platforms, and deepfake-related repercussions.Research limitations/implicationsThe study offers crucial insights into the evolving nature of deepfakes as a socio-technical phenomenon and the significance of platform dynamics in deepfake production. It enables researchers to comprehend the cascading effects of deepfakes and positions them to evaluate deepfake-related risks and associated mitigation mechanisms.Practical implicationsThe framework that emerges from the study illustrates the influence of platforms on the evolution of deepfakes and assists platform stakeholders in introducing effective platform governance structures to combat the relentless proliferation of deepfakes and their consequences, as well as providing guidance for governments and policymakers to collaborate with platform leaders to set guardrails for deepfake engagement.Originality/valueDeepfakes have been extensively contested for both their beneficial and negative applications and have been accused of heralding an imminent epistemic threat that has been downplayed by some quarters. This diversity of viewpoints necessitates a comprehensive understanding of the phenomenon. In responding to this call, this is one of the first to establish a comprehensive, theoretically informed perspective on how individuals produce, process, and engage with deepfakes through a meta-synthesis of qualitative literature on deepfakes.

show abstract

Deepfake-Image Anti-Forensics with Adversarial Examples Attacks

Cited by 7 publications

References 29 publications

Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack

Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack

Systematic Review: Anti-Forensic Computer Techniques

Engaging with deepfakes: a meta-synthesis from the perspective of social shaping of technology theory

Contact Info

Product

Resources

About