Related papers: A Response to Glaze Purification via IMPRESS
The recent proliferation of diffusion models has made style mimicry effortless, enabling users to imitate unique artistic styles without authorization. In deployed platforms, this raises copyright and intellectual-property risks and calls…
Face images captured through the glass are usually contaminated by reflections. The non-transmitted reflections make the reflection removal more challenging than for general scenes, because important facial features are completely occluded.…
Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e.g., in the healthcare domain and dangerous environments. While the general usability of these techniques is high,…
In the past years, numerous methods have been introduced to reliably detect digital face image manipulations. Lately, the generalizability of these schemes has been questioned in particular with respect to image post-processing. Image…
The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collapse. To address this…
Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate,…
Learned Image Compression (LIC) has recently become the trending technique for image transmission due to its notable performance. Despite its popularity, the robustness of LIC with respect to the quality of image reconstruction remains…
Adversarial robustness is one of the most challenging problems in Deep Learning and Computer Vision research. All the state-of-the-art techniques require a time-consuming procedure that creates cleverly perturbed images. Due to its cost,…
The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the clean images through the reverse process. Due to the lack of…
The rapid advancement of text-to-image generation systems, exemplified by models like Stable Diffusion, Midjourney, Imagen, and DALL-E, has heightened concerns about their potential misuse. In response, companies like Meta and Google have…
To sanitize specific concepts from imagery and text, privacy mechanisms with formal guarantees are often eschewed in practice in favor of more intuitive techniques. AI-based sanitization is poised to grow in popularity because it can work…
In this work we generalize the entanglement of purification and its conjectured holographic dual to conditional and multipartite versions of the same, where the optimization defining the entanglement of purification is now optimized in…
Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models. However, existing CLIP-guided image morphing methods encounter…
Perturbative availability poisons (PAPs) add small changes to images to prevent their use for model training. Current research adopts the belief that practical and effective approaches to countering PAPs do not exist. In this paper, we…
Photon subtraction can enhance entanglement, which for pure states induces a decrease in the purity of reduced states. In contrast, by analyzing the purities of Gaussian states before and after subtracting a single photon, we prove that the…
The textile industry is searching for innovative production techniques to improve the product quality, as well as society requires new finishing techniques working in environmental respect. Plasma surface treatments show distinct…
Plagiarism detection in programming education faces growing challenges due to increasingly sophisticated obfuscation techniques, particularly automated refactoring-based attacks. While code plagiarism detection systems used in education…
Plagiarism in programming assignments is a persistent issue in computer science education, increasingly complicated by the emergence of automated obfuscation attacks. While software plagiarism detectors are widely used to identify…
Untrusted data used to train a model might have been manipulated to endow the learned model with hidden properties that the data contributor might later exploit. Data purification aims to remove such manipulations prior to training the…
Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as…