相关论文: R.A.C.E.: Robust Adversarial Concept Erasure for S…

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…

Adversarial camouflage is a widely used physical attack against vehicle detectors for its superiority in multi-view attack performance. One promising approach involves using differentiable neural renderers to facilitate adversarial…

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…

Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired…

Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the…

While deep learning based image retrieval is reported to be vulnerable to adversarial attacks, existing works are mainly on image-to-image retrieval with their attacks performed at the front end via query modification. By contrast, we…

Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing…

ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR…

Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by…

Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when suppressing selected neurons entirely. This occurs because…

Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust…

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that T2I model can generate unsafe images…

The widespread adoption of deep neural networks in computer vision applications has brought forth a significant interest in adversarial robustness. Existing research has shown that maliciously perturbed inputs specifically tailored for a…

This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition…

Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptability to the generative process. We propose Diffusion Adaptive…

Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been…

Diffusion based text-to-image models are trained on large datasets scraped from the Internet, potentially containing unacceptable concepts (e.g., copyright-infringing or unsafe). We need concept removal techniques (CRTs) which are i)…

Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting…