paper-with-me

Papers Hard-label Attack

“Hard-label Attack” 태그가 달린 논문 9편 · 필터 해제

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

2024-02-02 · NeurIPS 2023 11 · Han Liu, Zhi Xu, Xiaotong Zhang, Feng Zhang 외

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this prob…

Adversarial AttackHard-label AttackNatural Language InferenceSemantic Similarity+3

DTA: Distribution Transform-based Attack for Query-Limited Scenario

2023-12-12 · Renyang Liu, Wei Zhou, Xin Jin, Song Gao 외

In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in tho…

Hard-label Attack

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

2023-08-01 · Hai Zhu, Zhaoqing Yang, Weiwei Shang, Yuren Wu

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples.…

Adversarial AttackHard-label Attack

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack

2022-01-20 · Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely inv…

Adversarial AttackHard-label AttackNatural Language InferencePrediction+2

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

2021-11-15 · NeurIPS 2021 12 · Chen Ma, Xiangyu Guo, Li Chen, Jun-Hai Yong 외

One major problem in black-box adversarial attacks is the high query complexity in the hard-label attack setting, where only the top-1 predicted label is available. In this paper, we propose a novel geometric-based appro…

Hard-label Attack

Learning-based Memetic Algorithm for Hard-label Textual Attack

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Deep neural networks are widely known to be vulnerable to adversarial examples in Natural Language Processing. However, existing textual adversarial attacks usually utilize the gradient or prediction confidence to genera…

Combinatorial OptimizationHard-label AttackNatural Language Inferencetext-classification+1

PredCoin: Defense against Query-based Hard-label Attack

2021-02-04 · Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar, Ang Li 외

Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new class of query-based hard-label (QBHL) black…

Hard-label Attack

RayS: A Ray Searching Method for Hard-label Adversarial Attack

2020-06-23 · Jinghui Chen, Quanquan Gu

Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the attacker only has access to the hard-label …

Adversarial AttackHard-label Attack

Sign-OPT: A Query-Efficient Hard-label Adversarial Attack

2019-09-24 · ICLR 2020 1 · Minhao Cheng, Simranjit Singh, Patrick Chen, Pin-Yu Chen 외

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited…

Adversarial AttackAdversarial RobustnessHard-label Attack
1–9 / 9