English
Related papers

Related papers: Backdoors to Acyclic SAT

200 papers

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Artificial Intelligence · Computer Science 2022-09-08 Bingchen Jiang , Zhao Li

Since training a large-scale backdoored model from scratch requires a large training dataset, several recent attacks have considered to inject backdoors into a trained clean model without altering model behaviors on the clean data. Previous…

Machine Learning · Computer Science 2022-03-03 Zhiyuan Zhang , Lingjuan Lyu , Weiqiang Wang , Lichao Sun , Xu Sun

We consider a CNF formula $F$ as a multiset of clauses: $F=\{c_1,..., c_m\}$. The set of variables of $F$ will be denoted by $V(F)$. Let $B_F$ denote the bipartite graph with partite sets $V(F)$ and $F$ and with an edge between $v \in V(F)$…

Data Structures and Algorithms · Computer Science 2012-12-04 R. Crowston , G. Gutin , M. Jones , V. Raman , S. Saurabh , A. Yeo

We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differently on a particular input known as the "trigger", while…

Machine Learning · Computer Science 2025-02-12 Paul Christiano , Jacob Hilton , Victor Lecomte , Mark Xu

In this paper we propose a structural parameter of CNF formulas and use it to identify instances of weighted MaxSAT and #SAT that can be solved in polynomial time. Given a CNF formula we say that a set of clauses is precisely satisfiable if…

Data Structures and Algorithms · Computer Science 2014-02-27 Sigve Hortemo Sæther , Jan Arne Telle , Martin Vatshelle

Object detection models, widely used in security-critical applications, are vulnerable to backdoor attacks that cause targeted misclassifications when triggered by specific patterns. Existing backdoor defense techniques, primarily designed…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Xianda Zhang , Siyuan Liang

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…

Artificial Intelligence · Computer Science 2023-03-14 Zaixi Zhang , Qi Liu , Zhicai Wang , Zepu Lu , Qingyong Hu

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Gorka Abad , Jing Xu , Stefanos Koffas , Behrad Tajalli , Stjepan Picek , Mauro Conti

Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes. Although backdoor…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Jun Xia , Zhihao Yue , Yingbo Zhou , Zhiwei Ling , Xian Wei , Mingsong Chen

In the Max $k$-Weight SAT (aka Max SAT with Cardinality Constraint) problem, we are given a CNF formula with $n$ variables and $m$ clauses together with a positive integer $k$. The goal is to find an assignment where at most $k$ variables…

Data Structures and Algorithms · Computer Science 2024-06-05 Pasin Manurangsi

As a critical threat to deep neural networks (DNNs), backdoor attacks can be categorized into two types, i.e., source-agnostic backdoor attacks (SABAs) and source-specific backdoor attacks (SSBAs). Compared to traditional SABAs, SSBAs are…

Cryptography and Security · Computer Science 2022-12-20 Shang Wang , Yansong Gao , Anmin Fu , Zhi Zhang , Yuqing Zhang , Willy Susilo , Dongxi Liu

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Emily Wenger , Josephine Passananti , Arjun Bhagoji , Yuanshun Yao , Haitao Zheng , Ben Y. Zhao

As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Baoyuan Wu , Hongrui Chen , Mingda Zhang , Zihao Zhu , Shaokui Wei , Danni Yuan , Mingli Zhu , Ruotong Wang , Li Liu , Chao Shen

Extensive literature on backdoor poison attacks has studied attacks and defenses for backdoors using "digital trigger patterns." In contrast, "physical backdoors" use physical objects as triggers, have only recently been identified, and are…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Emily Wenger , Roma Bhattacharjee , Arjun Nitin Bhagoji , Josephine Passananti , Emilio Andere , Haitao Zheng , Ben Y. Zhao

The Local Lemma is a fundamental tool of probabilistic combinatorics and theoretical computer science, yet there are hardly any natural problems known where it provides an asymptotically tight answer. The main theme of our paper is to…

Combinatorics · Mathematics 2016-04-21 Heidi Gebauer , Tibor Szabo , Gabor Tardos

Causal effect estimation from observational data is a fundamental task in empirical sciences. It becomes particularly challenging when unobserved confounders are involved in a system. This paper focuses on front-door adjustment -- a classic…

Artificial Intelligence · Computer Science 2024-01-29 Marcel Wienöbst , Benito van der Zander , Maciej Liśkiewicz

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By…

Cryptography and Security · Computer Science 2023-05-19 Xinrui Liu , Yajie Wang , Yu-an Tan , Kefan Qiu , Yuanzhang Li

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses…

Cryptography and Security · Computer Science 2022-12-20 Wanlun Ma , Derui Wang , Ruoxi Sun , Minhui Xue , Sheng Wen , Yang Xiang

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…

Combinatorics · Mathematics 2011-02-02 Arup Kumar Ghosh