Related papers: TrojFlow: Flow Models are Natural Targets for Troj…
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…
Recent optical flow methods are almost exclusively judged in terms of accuracy, while their robustness is often neglected. Although adversarial attacks offer a useful tool to perform such an analysis, current attacks on optical flow methods…
Flow Matching has recently emerged as a popular class of generative models for simulating a target distribution $\mu_1$ from samples drawn from a source distribution $\mu_0$. This framework relies on a fixed coupling between $\mu_0$ and…
Generative models learn the distribution of data from a sample dataset and can then generate new data instances. Recent advances in deep learning has brought forth improvements in generative model architectures, and some state-of-the-art…
In response to Distributed Denial of Service (DDoS) attacks, recent research efforts increasingly rely on Machine Learning (ML)-based solutions, whose effectiveness largely depends on the quality of labeled training datasets. To address the…
Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging…
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…
State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…
Perimeter control maintains high traffic efficiency within protected regions by controlling transfer flows among regions to ensure that their traffic densities are below critical values. Existing approaches can be categorized as either…
Deep neural networks are susceptible to adversarial attacks, which pose a significant threat to their security and reliability in real-world applications. The most notable adversarial attacks are transfer-based attacks, where an adversary…
The proficiency of Large Language Models (LLMs) in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate…
Modeling complex fluid systems, especially turbulence governed by partial differential equations (PDEs), remains a fundamental challenge in science and engineering. Recently, diffusion-based generative models have gained attention as a…
Network intrusion detection systems (NIDS) are an essential defense for computer networks and the hosts within them. Machine learning (ML) nowadays predominantly serves as the basis for NIDS decision making, where models are tuned to reduce…
Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…
Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which…
HTTP-based Trojan is extremely threatening, and it is difficult to be effectively detected because of its concealment and confusion. Previous detection methods usually are with poor generalization ability due to outdated datasets and…
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…
Modeling stochastic and irregularly sampled time series is a challenging problem found in a wide range of applications, especially in medicine. Neural stochastic differential equations (Neural SDEs) are an attractive modeling technique for…