相关论文: Content-Adaptive Pixel Discretization to Improve M…

Adversarial examples for diffusion models are widely used as solutions for safety concerns. By adding adversarial perturbations to personal images, attackers can not edit or imitate them easily. However, it is essential to note that all…

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images. To defend against adversarial attacks in a training-free and attack-agnostic manner, this…

Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress…

The vulnerability of deep neural networks to adversarial examples, which are crafted maliciously by modifying the inputs with imperceptible perturbations to misled the network produce incorrect outputs, reveals the lack of robustness and…

The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks. To solve this problem, we introduce a generative deep…

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

This paper investigates the robustness of vision-language models against adversarial visual perturbations and introduces a novel ``double visual defense" to enhance this robustness. Unlike previous approaches that resort to lightweight…

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…

Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified…

Minute pixel changes in an image drastically change the prediction that the deep learning model makes. One of the most significant problems that could arise due to this, for instance, is autonomous driving. Many methods have been proposed…

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base…

Many defenses against adversarial attacks (\eg robust classifiers, randomization, or image purification) use countermeasures put to work only after the attack has been crafted. We adopt a different perspective to introduce $A^5$…

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized…

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Could we compress images via standard codecs while avoiding visible artifacts? The answer is obvious -- this is doable as long as the bit budget is generous enough. What if the allocated bit-rate for compression is insufficient? Then…

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

Recently developed text-to-image diffusion models make it easy to edit or create high-quality images. Their ease of use has raised concerns about the potential for malicious editing or deepfake creation. Imperceptible perturbations have…

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The…