Related papers: TARO: Temporal Adversarial Rectification Optimizat…
Deep learning models, even the-state-of-the-art ones, are highly vulnerable to adversarial examples. Adversarial training is one of the most efficient methods to improve the model's robustness. The key factor for the success of adversarial…
Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE)…
Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic…
Recent findings suggest that diffusion models significantly enhance empirical adversarial robustness. While some intuitive explanations have been proposed, the precise mechanisms underlying these improvements remain unclear. In this work,…
Stochastic Optimization (SO) is a classical approach for optimization under uncertainty that typically requires knowledge about the probability distribution of uncertain parameters. As the latter is often unknown, Distributionally Robust…
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility…
Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically requires…
Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion…
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoising are typical strategies for defending adversarial…
The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Since inverse problems inherently entail maximum a posteriori estimation,…
We question the current evaluation practice on diffusion-based purification methods. Diffusion-based purification methods aim to remove adversarial effects from an input data point at test time. The approach gains increasing attention as an…
Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although…
Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…
Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…
Face authentication systems have brought significant convenience and advanced developments, yet they have become unreliable due to their sensitivity to inconspicuous perturbations, such as adversarial attacks. Existing defenses often…
Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data…
Diffusion models have emerged as powerful generative priors for solving PDE-constrained inverse problems. Compared to end-to-end approaches relying on massive paired datasets, explicitly decoupling the prior distribution of physical…
Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…
Adversarial attacks have become a well-explored domain, frequently serving as evaluation baselines for model robustness. Among these, black-box attacks based on transferability have received significant attention due to their practical…
Diffusion-based generators set the current state of the art for synthetic tabular data. These methods approach but rarely exceed real-data utility, and closing this synthetic-real gap has so far been pursued exclusively at training time,…