相关论文: Transferable Dual-Domain Feature Importance Attack…

Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Adversarial examples are a key method to exploit deep neural networks. Using gradient information, such examples can be generated in an efficient way without altering the victim model. Recent frequency domain transformation has further…

The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although…

Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges in applying prevailing image recognition…

Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image tasks that take an input image and generate an output…

Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attention since it can alleviate performance degradation due to the…

Face Recognition (FR) models are vulnerable to adversarial examples that subtly manipulate benign face images, underscoring the urgent need to improve the transferability of adversarial attacks in order to expose the blind spots of these…

Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…

Transferability-based adversarial attacks exploit the ability of adversarial examples, crafted to deceive a specific source Intrusion Detection System (IDS) model, to also mislead a target IDS model without requiring access to the training…

Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across different domains due to insufficient intrinsic interactions. These…

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…

Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy. To investigate this privacy…

The security of AI-generated content (AIGC) detection is crucial for ensuring multimedia content credibility. To enhance detector security, research on adversarial attacks has become essential. However, most existing adversarial attacks…

With the steady rise of the use of AI in bio-technical applications and the widespread adoption of genomics sequencing, an increasing amount of AI-based algorithms and tools is entering the research and production stage affecting critical…

Test-time defenses are used to improve the robustness of deep neural networks to adversarial examples during inference. However, existing methods either require an additional trained classifier to detect and correct the adversarial samples,…

Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility.…

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…