paper-with-me

홈 › Papers

Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making

2023-05-27 · Xuanjie Fang, Sijie Cheng, Yang Liu, Wei Wang

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage framework to attack without considering the subsequent influence of substitution at each step. In this paper, we formally model the adversarial attack task on PLMs as a sequential decision-making problem, where the whole attack process is sequential with two decision-making problems, i.e., word finder and word substitution. Considering the attack process can only receive the final state without any direct intermediate signals, we propose to use reinforcement learning to find an appropriate sequential attack path to generate adversaries, named SDM-Attack. Extensive experimental results show that SDM-Attack achieves the highest attack success rate with a comparable modification rate and semantic similarity to attack fine-tuned BERT. Furthermore, our analyses demonstrate the generalization and transferability of SDM-Attack. The code is available at https://github.com/fduxuan/SDM-Attack.

📄 PDF Abstract BibTeX arXiv:2305.17440

Code (1)

fduxuan/sdm-attack 공식 구현 pytorch

Tasks

Adversarial AttackDecision MakingSemantic SimilaritySemantic Textual SimilaritySequential Decision Making

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
WordPiece 설명 없음
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Black-Box Attacks against RNN based Malware Detection Algorithms

2017-05-23 · Weiwei Hu, Ying Tan

Recent researches have shown that machine learning based malware detection algorithms are very vulnerable under the attacks of adversarial examples. These works mainly focused on the detection algorithms which use featur…

Malware Detection

Adaptive Adversarial Attack on Scene Text Recognition

2018-07-09 · Xiaoyong Yuan, Pan He, Xiaolin Andy Li, Dapeng Oliver Wu

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adv…

Adversarial Attackimage-classificationImage ClassificationObject Detection+2

Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders

2022-07-19 · Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang 외

While sequential recommender systems achieve significant improvements on capturing user dynamics, we argue that sequential recommenders are vulnerable against substitution-based profile pollution attacks. To demonstrate …

Adversarial AttackAdversarial DefenseRecommendation Systems

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization

2022-06-17 · Deokjae Lee, Seungyong Moon, Junhyeok Lee, Hyun Oh Song

We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model. Exis…

Bayesian Optimization

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

2024-02-16 · Ziyi Yin, Muchao Ye, Tianrong Zhang, Jiaqi Wang 외

Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the a…

Adversarial RobustnessLanguage ModellingLarge Language ModelQuestion Answering+2