paper-with-me

Papers

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

2018-02-22 · NeurIPS 2018 12 · Gamaleldin F. Elsayed, Shreya Shankar, Brian Cheung, Nicolas Papernot, Alex Kurakin, Ian Goodfellow, Jascha Sohl-Dickstein

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.

📄 PDF Abstract BibTeX arXiv:1802.08195

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningOpen-Ended Question Answering

Similar Papers 제목 키워드 기반

Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples

2023-05-01 · Chenshuang Zhang, Chaoning Zhang, Taegoo Kang, Donghun Kim 외

Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks in a zero-short manner. Computer vision (CV) area might follow the natural language…

Adversarial AttackAdversarial Robustness

Advbox: a toolbox to generate adversarial examples that fool neural networks

2020-01-13 · Dou Goodman, Hao Xin, Wang Yang, Wu Yuesheng 외

In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Rece…

BIG-bench Machine LearningFace RecognitionFace Swapping

Note on Attacking Object Detectors with Adversarial Stickers

2017-12-21 · Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li 외

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversar…

Deep LearningObject

Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs

2024-09-09 · Yahya Jabary, Andreas Plesner, Turlan Kuzhagaliyev, Roger Wattenhofer

Modern CAPTCHAs rely heavily on vision tasks that are supposedly hard for computers but easy for humans. However, advances in image recognition models pose a significant threat to such CAPTCHAs. These models can easily b…

Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems

2023-03-13 · Islam Debicha, Benjamin Cochez, Tayeb Kenaza, Thibault Debatty 외

Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally cr…

Intrusion DetectionNetwork Intrusion Detection