Related papers: Rethinking Robust Adversarial Concept Erasure in D…

Applying generative adversarial networks (GANs) to text-related tasks is challenging due to the discrete nature of language. One line of research resolves this issue by employing reinforcement learning (RL) and optimizing the next-word…

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and…

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

Recent advances in diffusion models have significantly enhanced image generation capabilities. However, customizing these models with new classes often leads to unintended consequences that compromise their reliability. We introduce the…

With the rapid growth of text-to-image models, a variety of techniques have been suggested to prevent undesirable image generations. Yet, these methods often only protect against specific user prompts and have been shown to allow unsafe…

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, particularly in safety-critical applications. We propose a novel…

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the…

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…

We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…

Despite the rapid development of adversarial machine learning, most adversarial attack and defense researches mainly focus on the perturbation-based adversarial examples, which is constrained by the input images. In comparison with existing…

Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

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…

Semantic segmentation is a task that traditionally requires a large dataset of pixel-level ground truth labels, which is time-consuming and expensive to obtain. Recent advancements in the weakly-supervised setting show that reasonable…

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…