English
Related papers

Related papers: Backdoors to Acyclic SAT

200 papers

We aim at providing a foundation of a theory of "good" SAT representations F of boolean functions f. We argue that the hierarchy UC_k of unit-refutation complete clause-sets of level k, introduced by the authors, provides the most basic…

Artificial Intelligence · Computer Science 2013-05-13 Matthew Gwynne , Oliver Kullmann

Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone to catastrophic overfitting (CO), wherein models overfit to…

Machine Learning · Computer Science 2026-04-28 Mengnan Zhao , Lihe Zhang , Tianhang Zheng , Bo Wang , Baocai Yin

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Cryptography and Security · Computer Science 2024-12-03 Pengfei He , Yue Xing , Han Xu , Jie Ren , Yingqian Cui , Shenglai Zeng , Jiliang Tang , Makoto Yamada , Mohammad Sabokrou

There have been several efforts in backdoor attacks, but these have primarily focused on the closed-set performance of classifiers (i.e., classification). This has left a gap in addressing the threat to classifiers' open-set performance,…

Machine Learning · Computer Science 2024-12-09 ZeinabSadat Taghavi , Hossein Mirzaei

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms…

Machine Learning · Computer Science 2022-10-20 Baoyuan Wu , Hongrui Chen , Mingda Zhang , Zihao Zhu , Shaokui Wei , Danni Yuan , Chao Shen

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

Cryptography and Security · Computer Science 2025-11-12 Zihan Wang , Rui Zhang , Hongwei Li , Wenshu Fan , Wenbo Jiang , Qingchuan Zhao , Guowen Xu

Recently, backdoor attacks have become an emerging threat to the security of machine learning models. From the adversary's perspective, the implanted backdoors should be resistant to defensive algorithms, but some recently proposed…

Machine Learning · Computer Science 2024-07-23 Hoang Pham , The-Anh Ta , Anh Tran , Khoa D. Doan

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…

Machine Learning · Computer Science 2021-12-02 Yige Li , Xixiang Lyu , Nodens Koren , Lingjuan Lyu , Bo Li , Xingjun Ma

It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a small set of training samples. Although a line of defense…

Machine Learning · Computer Science 2023-10-24 Rui Min , Zeyu Qin , Li Shen , Minhao Cheng

In the estimation of causal effects, one common method for removing the influence of confounders is to adjust the variables that satisfy the back-door criterion. However, it is not always possible to uniquely determine sets of such…

Machine Learning · Computer Science 2025-02-06 Atsushi Noda , Takashi Isozaki

Hidden confounders that influence both states and actions can bias policy learning in reinforcement learning (RL), leading to suboptimal or non-generalizable behavior. Most RL algorithms ignore this issue, learning policies from…

Machine Learning · Computer Science 2025-06-09 Thanh Vinh Vo , Young Lee , Haozhe Ma , Chien Lu , Tze-Yun Leong

We study random instances of the weighted $d$-CNF satisfiability problem (WEIGHTED $d$-SAT), a generic W[1]-complete problem. A random instance of the problem consists of a fixed parameter $k$ and a random $d$-CNF formula $\weicnf{n}{p}{k,…

Data Structures and Algorithms · Computer Science 2008-12-18 Yong Gao

(k,s)-SAT is the satisfiability problem restricted to instances where each clause has exactly k literals and every variable occurs at most s times. It is known that there exists a function f such that for s\leq f(k) all (k,s)-SAT instances…

Combinatorics · Mathematics 2007-05-23 Shlomo Hoory , Stefan Szeider

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

The aim of this short note is mainly pedagogical. It summarizes some knowledge about Boolean satisfiability (SAT) and the P=NP? problem in an elementary mathematical language. A convenient scheme to visualize and manipulate CNF formulae is…

Computational Complexity · Computer Science 2014-08-15 Bernd R. Schuh

Given a CNF formula and a weight for each assignment of values to variables, two natural problems are weighted model counting and distribution-aware sampling of satisfying assignments. Both problems have a wide variety of important…

Artificial Intelligence · Computer Science 2014-04-14 Supratik Chakraborty , Daniel J. Fremont , Kuldeep S. Meel , Sanjit A. Seshia , Moshe Y. Vardi

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Cryptography and Security · Computer Science 2021-05-03 Yulong Tian , Fnu Suya , Fengyuan Xu , David Evans

A generalized 1-in-3SAT problem is defined and found to be in complexity class P when restricted to a certain subset of CNF expressions. In particular, 1-in-kSAT with no restrictions on the number of literals per clause can be decided in…

Computational Complexity · Computer Science 2017-07-04 Bernd R. Schuh

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial…

Machine Learning · Computer Science 2021-08-02 Mustafa Safa Ozdayi , Murat Kantarcioglu , Yulia R. Gel

We present a very general approach to learning the structure of causal models based on d-separation constraints, obtained from any given set of overlapping passive observational or experimental data sets. The procedure allows for both…

Artificial Intelligence · Computer Science 2013-09-27 Antti Hyttinen , Patrik O. Hoyer , Frederick Eberhardt , Matti Jarvisalo
‹ Prev 1 3 4 5 6 7 10 Next ›