Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 8,284 papers for “linear attack”

Linear Program Powered Attack

Ismaïla Seck, Gaëlle Loosli, Stéphane Canu · 2021

Finding the exact robust test error is a good way to compare the robustness of neural networks, but it is a difficult task even on small networks and datasets like MNIST. However, finding reasonable lower and upper bounds is possible and can be done using either complete methods or attacks. On the one hand, complete methods such as Mixed Integer Program (MIP) give exact robust test accuracy but are time-consuming. On the other hand, attacks are usually fast but tend to perform badly against robust networks and underestimate the lower bound on the robust test error. The purpose of this paper is to present a novel attack method that is both fast and gives better lower bounds than previous attacks. This method exploits the algebraic properties of networks with piecewise linear activation functions to partition the input space in such a way that for each subset of that partition, finding the local optimal adversarial example is done by solving a linear program. Moving from one subset to another is done using classical gradient-based attack tools. To evaluate the quality of the produced adversarial examples, we compare our lower bound on the robust test error to the one previously found. The results found are satisfying in the sense that it does better than previous lower bounds on several models and finds adversarial examples that the MIP failed to expose before reaching its time limit.

Cited by 1

Incremental Linear Regression Attack

Juncheng Chen, Jun-Sheng Ng, Nay Aung Kyaw et al. · 2022

Linear Regression Attack (LRA) is an effective Side-Channel Analysis (SCA) distinguisher designed to overcome the inaccuracies in leakage models (e.g, Hamming Weight). However, the implementation of the original LRA (termed as baseline LRA) involves many matrix arithmetic operations. The sizes of these matrices are determined by the scale of the Physical Leakage Information (PLI) traces. When processing large-scale PLI traces, extremely high memory capacity is required to execute the baseline LRA. In this paper, we propose a new implementation of LRA coined as incremental LRA. Theoretically, we reformulate the process of baseline LRA to break down the large dataset and process smaller batches of the dataset iteratively. Experimentally, we first validate that our proposed incremental LRA provides flexible choice of batch size and enables a progressive increase on the PLI traces to present attack results incrementally. Second, our proposed incremental LRA reduces execution memory and time significantly as compared to the baseline LRA. We demonstrate that the best execution performance of our incremental LRA requires only 0.65% of memory requirement (154x smaller) and takes only 3.37% of the processing time (30x speed-up) of the baseline LRA while attacking the same amount of traces.

Cited by 2

A linear decomposition attack

Alexei Myasnikov, В. А. Романьков · journal of Groups complexity cryptology · 2015

Abstract We discuss a new attack, termed a

Cited by 42

Improved integral attack——random linear distinguish and key recovery attack

Shaoyu DU · SHILAP Revista de lepidopterología · 2023

Based on the integral attack and collision attack of four rounds of AES, a random linear distinguish attack against four rounds of SP block ciphers was proposed, which took advantage of the non-uniformity of linear biases’ distribution between some blocks of plaintext and inner state.Combined with precomputation, a key recovery attack against four rounds of AES-like block ciphers was proposed.For LED-64, the results of distinguish attack and key recovery attack were given.Therein for LED-64 of 1-Step, the probability of successful distinguish attack is 85% under the condition that the data complexity is 2<sup>8</sup> and the computational complexity is 2<sup>16</sup> basic operation.For LED-64 of 2-Step, the calculation complexity of the key recovery attack under the condition of related key is 2<sup>14</sup> basic operation, the data complexity is 2<sup>8</sup>, and the precomputation storage complexity is 2<sup>38</sup> half bytes.

Cited by 0Open access

Rotational Differential-Linear Attack on Chaskey

Yuan Qin, Gaoli Wang, Guoyan Zhang · Security and Communication Networks · 2022

Rotational/Rotational-XOR differential-linear attack is a kind of powerful attack on ARX primitives. In this paper, we analyse the message authentication code algorithm—Chaskey—by using rotational differential-linear attack and using partitioning technique for key recovery. We presentthe results of distinguishing attack under weak-key and related-key settingswith correlation <math xmlns="http://www.w3.org/1998/Math/MathML" id="M1"> <msup> <mrow> <mn>2</mn> </mrow> <mrow> <mo>−</mo> <mn>55.636</mn> </mrow> </msup> </math> for 9-round Chaskey. This is for the first time rotational differential-linear distinguisher has been used to analyse Chaskey. It is concluded that Chaskey can resist against rotational differential-linear attack.

Cited by 0Open access

Linear Distinguishing Attack on Shannon Algorithm

Chang Ya-qin, Chen‐hui Jin · JOURNAL OF ELECTRONICS INFORMATION TECHNOLOGY · 2011

摘要: 该文基于对Shannon算法非线性反馈移存器反馈函数和非线性滤波函数进行线性逼近,得到了优势为2-28的32个新的区分器,给出了一个对流密码算法Shannon的新的线性区分攻击。该区分攻击大约需要252密钥字就能将Shannon算法的密钥流序列从随机序列中区分出来。 关键词: 序列密码 / 区分攻击 / 线性逼近 / 非线性反馈移存器 / Shannon算法

Cited by 0Open access

Linear Interpolation Method for Adversarial Attack

CHEN Jun, ZHOU Qiang, BAO Lei, TAO Qing · SHILAP Revista de lepidopterología · 2025

Deep neural networks exhibit significant vulnerability in the face of adversarial examples and are prone to attacks.The construction of adversarial examples can be abstracted as an optimization problem that maximizes the objective function.How-ever,gradient-based iterative methods often face convergence challenges when dealing with such optimization problems.These methods primarily rely on the gradient sign for iterative updates,neglecting the magnitude and direction information of the gra-dient,which can lead to algorithm instability.Studies have shown that the I-FGSM adversarial attack algorithm originates from the stochastic projection subgradient method in the field of optimization.Literature has indicated that in optimization problems,using linear interpolation methods to replace stochastic projection subgradient methods can achieve superior performance.Based on this,this paper proposes a novel linear interpolation-based adversarial attack method,which applies the interpolation strategy to adversarial attacks and replaces the traditional sign gradient with the actual gradient.Theoretically,the proposed linear interpolation adversarial attack algorithm is proved can achieve the optimal individual convergence rate in general convex optimization pro-blems,thereby overcoming the convergence difficulties of sign gradient-based algorithms.Experimental results confirm that the linear interpolation method,as a universal and efficient strategy,when combined with gradient-based adversarial attack methods,can form new attack algorithms.Compared to the original algorithms,these new algorithms significantly increase the success rate of attacks while maintaining the imperceptibility of adversarial examples and exhibit high stability during the iterative process.

Cited by 0Open access

SLAP – Simple Linear Attack for Perceptron

Andrey Igorevich Perminov · Proceedings of the Institute for System Programming of RAS · 2024

This article introduces a new approach to tricking perceptron based neural networks with piecewise linear activation functions using basic linear algebra. By formulating the attack as a system of linear equations and inequalities, it demonstrates a streamlined and computationally efficient approach to generating diverse sets of adversarial examples. The algorithms for the proposed attack have been implemented in code, that accessible in the open-source repository. The study highlights the formidable challenge posed by the proposed attack methodology for contemporary neural network defenses, emphasizing the pressing need for innovative defense strategies. Through a comprehensive exploration of adversarial vulnerabilities, this research contributes to the advancement of adversarial robustness in machine learning, paving the way for the development of more reliable and trustworthy artificial intelligence systems in real-world applications.

Cited by 0Open access

A Linear Distinguishing Attack on Scream

Alexander Maximov, Thomas Johansson · IEEE Transactions on Information Theory · 2007

A linear distinguishing attack on the stream cipher Scream is proposed. When the keystream is of length 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">98</sup> words, the distinguisher has a detectable advantage. When the keystream length is around 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">120</sup> the advantage is very close to 1. This shows certain weaknesses of Scream. In the process, the paper introduces new general ideas on how to improve the performance of linear distinguishing attacks on stream ciphers.

Cited by 13

Attack time analysis in dynamic attack trees via integer linear programming

Milan Lopuhaä-Zwakenberg, Mariëlle Stoelinga · arXiv (Cornell University) · 2021

Attack trees (ATs) are an important tool in security analysis, and an important part of AT analysis is computing metrics. However, metric computation is NP-complete in general. In this paper, we showcase the use of mixed integer linear programming (MILP) as a tool for quantitative analysis. Specifically, we use MILP to solve the open problem of calculating the min time metric of dynamic ATs, i.e., the minimal time to attack a system. We also present two other tools to further improve our MILP method: First, we show how the computation can be sped up by identifying the modules of an AT, i.e. subtrees connected to the rest of the AT via only one node. Second, we define a general semantics for dynamic ATs that significantly relaxes the restrictions on attack trees compared to earlier work, allowing us to apply our methods to a wide variety of ATs. Experiments on a synthetic testing set of large ATs verify that both the integer linear programming approach and modular analysis considerably decrease the computation time of attack time analysis.

Cited by 2Open access

Sensor attack avoidance: Linear quadratic game approach

Dongxu Li, Genshe Chen, Erik Blasch et al. · 2009

For reliable and sustainable decision making, it is essential to perform intelligent sensing and data collection at scalable network resources costs. The sensor platforms used in a warfare may be under attacks from adversarial forces, which will largely impact the overall performance of surveillance systems. Thus, it is crucial that each intelligent sensor have the capability of detecting and avoiding possible attacks. In this paper, we study an attack-avoidance problem under the framework of a LQ game formulation. This is a first attempt to solve such kind of problems. From a practical point of view, the inherent hard constraints have been approximated and replaced by soft constraints with a fixed optimization horizon. For implementation, a receding horizon scheme has been used in junction with the LQ strategies. Overall, the LQ strategies can provide good control guidance laws for the players.

Cited by 12