English
Related papers

Related papers: A Game-Theoretic Analysis of Adversarial Classific…

200 papers

Adversarial training is a standard technique for training adversarially robust models. In this paper, we study adversarial training as an alternating best-response strategy in a 2-player zero-sum game. We prove that even in a simple…

Machine Learning · Computer Science 2023-03-01 Maria-Florina Balcan , Rattana Pukdee , Pradeep Ravikumar , Hongyang Zhang

With the recent developments in artificial intelligence and machine learning, anomalies in network traffic can be detected using machine learning approaches. Before the rise of machine learning, network anomalies which could imply an…

Machine Learning · Computer Science 2020-04-10 Aritran Piplai , Sai Sree Laya Chukkapalli , Anupam Joshi

When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly…

Machine Learning · Computer Science 2026-03-09 Soyon Choi , Scott Alfeld , Meiyi Ma

We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class of data passed to it as a query. However, along with queries…

Machine Learning · Computer Science 2020-02-11 Prithviraj Dasgupta , Joseph B. Collins , Michael McCarrick

We propose a new variant of the strategic classification problem: a principal reveals a classifier, and $n$ agents report their (possibly manipulated) features to be classified. Motivated by real-world applications, our model crucially…

Computer Science and Game Theory · Computer Science 2025-02-28 Safwan Hossain , Evi Micha , Yiling Chen , Ariel Procaccia

Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within…

Computer Vision and Pattern Recognition · Computer Science 2021-11-04 Nathan Drenkow , Neil Fendley , Philippe Burlina

Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…

Machine Learning · Computer Science 2024-01-08 Shorya Sharma

In the cybersecurity setting, defenders are often at the mercy of their detection technologies and subject to the information and experiences that individual analysts have. In order to give defenders an advantage, it is important to…

Cryptography and Security · Computer Science 2022-12-09 Erick Galinkin , Emmanouil Pountourakis , John Carter , Spiros Mancoridis

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 João Monteiro , Isabela Albuquerque , Zahid Akhtar , Tiago H. Falk

Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Alexis Winter , Jean-Vincent Martini , Romaric Audigier , Angelique Loesch , Bertrand Luvison

A significant threat to the recent, wide deployment of machine learning-based systems, including deep neural networks (DNNs), is adversarial learning attacks. We analyze possible test-time evasion-attack mechanisms and show that, in some…

Machine Learning · Computer Science 2018-06-29 David J. Miller , Yulia Wang , George Kesidis

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…

Cryptography and Security · Computer Science 2019-06-24 Liang Tong , Aron Laszka , Chao Yan , Ning Zhang , Yevgeniy Vorobeychik

In strategic classification, agents modify their features, at a cost, to ideally obtain a positive classification from the learner's classifier. The typical response of the learner is to carefully modify their classifier to be robust to…

Machine Learning · Computer Science 2024-02-15 Lee Cohen , Saeed Sharifi-Malvajerdi , Kevin Stangl , Ali Vakilian , Juba Ziani

This paper studies the sensor placement problem in a networked control system for improving its security against cyber-physical attacks. The problem is formulated as a zero-sum game between an attacker and a detector. The attacker's…

Optimization and Control · Mathematics 2018-09-25 Mohammad Pirani , Ehsan Nekouei , Henrik Sandberg , Karl Henrik Johansson

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…

Computer Vision and Pattern Recognition · Computer Science 2017-10-30 Xin Li , Fuxin Li

This paper investigates the strategic concealment of environment representations used by players in competitive games. We consider a defense scenario in which one player (the Defender) seeks to infer and exploit the representation used by…

Multiagent Systems · Computer Science 2026-03-04 Yue Guan , Dipankar Maity , Panagiotis Tsiotras

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yuhang Wu , Sunpreet S. Arora , Yanhong Wu , Hao Yang

In adversarial patrolling games, a mobile Defender strives to discover intrusions at vulnerable targets initiated by an Attacker. The Attacker's utility is traditionally defined as the probability of completing an attack, possibly weighted…

Multiagent Systems · Computer Science 2022-02-03 David Klaška , Antonín Kučera , Vít Musil , Vojtěch Řehák

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Machine Learning · Computer Science 2022-06-17 Florian Tramèr

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

Machine Learning · Computer Science 2022-06-24 Haojing Shen , Sihong Chen , Ran Wang , Xizhao Wang