相关论文: TrojFlow: Flow Models are Natural Targets for Troj…

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize the developed…

Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The…

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neural networks (GAN) usually requires large amounts of training…

Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match…

Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways. This paper proposes MISA,…

Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing parameter…

Flow Matching (FM) (also referred to as stochastic interpolants or rectified flows) stands out as a class of generative models that aims to bridge in finite time the target distribution $\nu^\star$ with an auxiliary distribution $\mu$,…

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively…

Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Directly regressing clean videos from adversarial inputs often…

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

In Natural Language Processing (NLP), intelligent neuron models can be susceptible to textual Trojan attacks. Such attacks occur when Trojan models behave normally for standard inputs but generate malicious output for inputs that contain a…

Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models…

Federated learning (FL) enables distributed clients to collaboratively train a global model using local private data. Nevertheless, recent studies show that conventional FL algorithms still exhibit deficiencies in privacy protection, and…

Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their…

Computing systems, including real-time embedded systems, are becoming increasingly connected to allow for more advanced and safer operation. Such embedded systems are resource-constrained, such as lower processing capabilities, as compared…

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has…

Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security implications of this widely-adopted practice remain critically…

Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models…

Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial…