相关论文: SAT Backdoors: Depth Beats Size

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

Monocular depth estimation using Convolutional Neural Networks (CNNs) has shown impressive performance in outdoor driving scenes. However, self-supervised learning of indoor depth from monocular sequences is quite challenging for…

Recently, a backdoor data poisoning attack was proposed, which adds mislabeled examples to the training set, with an embedded backdoor pattern, aiming to have the classifier learn to classify to a target class whenever the backdoor pattern…

We introduce the problem of finding a satisfying assignment to a CNF formula that must further belong to a prescribed input subspace. Equivalent formulations of the problem include finding a point outside a union of subspaces (the…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

In recent years, with the successful application of DNN in fields such as NLP and CV, its security has also received widespread attention. (Author) proposed the method of backdoor attack in Badnet. Switch implanted backdoor into the model…

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…

Control invariant sets are crucial for various methods that aim to design safe control policies for systems whose state constraints must be satisfied over an indefinite time horizon. In this article, we explore the connections among…

Federated Learning (FL) enables numerous participants to train deep learning models collaboratively without exposing their personal, potentially sensitive data, making it a promising solution for data privacy in collaborative training. The…

We show that the Satisfiability (SAT) problem for CNF formulas with {\beta}-acyclic hypergraphs can be solved in polynomial time by using a special type of Davis-Putnam resolution in which each resolvent is a subset of a parent clause. We…

Quantum neural networks (QNNs) succeed in object recognition, natural language processing, and financial analysis. To maximize the accuracy of a QNN on a Noisy Intermediate Scale Quantum (NISQ) computer, approximate synthesis modifies the…

We give a fixed-parameter tractable (FPT) approximation algorithm computing the path-width of a tournament, and more generally, of a semi-complete digraph. Based on this result, we prove that topological containment and rooted immersion…

Deep neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to…

Boolean Satisfiability solvers have gone through dramatic improvements in their performances and scalability over the last few years by considering symmetries. It has been shown that by using graph symmetries and generating symmetry…

In this paper, we prove that the general CNF satisfiability problem can be solved in $O^*(1.0638^L)$ time, where $L$ is the length of the input CNF-formula (i.e., the total number of literals in the formula), which improves the previous…

The recently introduced graph parameter tree-cut width plays a similar role with respect to immersions as the graph parameter treewidth plays with respect to minors. In this paper, we provide the first algorithmic applications of tree-cut…

Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor…

The success of deep neural networks (DNNs) in real-world applications has benefited from abundant pre-trained models. However, the backdoored pre-trained models can pose a significant trojan threat to the deployment of downstream DNNs.…