paper-with-me

Papers

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution

2021-08-29 · EMNLP 2021 11 · Zongyi Li, Jianhan Xu, Jiehang Zeng, Linyang Li, Xiaoqing Zheng, Qi Zhang, Kai-Wei Chang, Cho-Jui Hsieh

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin.

📄 PDF Abstract BibTeX arXiv:2108.12777

Code (1)

rockylzy/textdefender 공식 구현 pytorch

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

A Framework for Enhancing Deep Neural Networks Against Adversarial Malware

2020-04-15 · Deqiang Li, Qianmu Li, Yanfang Ye, Shouhuai Xu

Machine learning-based malware detection is known to be vulnerable to adversarial evasion attacks. The state-of-the-art is that there are no effective defenses against these attacks. As a response to the adversarial malw…

General ClassificationMalware ClassificationMalware Detection

The Path To Autonomous Cyber Defense

2024-04-12 · Sean Oesch, Phillipe Austria, Amul Chaulagain, Brian Weber 외

Defenders are overwhelmed by the number and scale of attacks against their networks.This problem will only be exacerbated as attackers leverage artificial intelligence to automate their workflows. We propose a path to au…

FedDefender: Backdoor Attack Defense in Federated Learning

2023-07-02 · Waris Gill, Ali Anwar, Muhammad Ali Gulzar

Federated Learning (FL) is a privacy-preserving distributed machine learning technique that enables individual clients (e.g., user participants, edge devices, or organizations) to train a model on their local data in a s…

Backdoor AttackData PoisoningFederated LearningImage Classification+2

A Bayesian Nash equilibrium-based moving target defense against stealthy sensor attacks

2021-11-12 · David Umsonst, Serkan Sarıtaş, György Dán, Henrik Sandberg

We present a moving target defense strategy to reduce the impact of stealthy sensor attacks on feedback systems. The defender periodically and randomly switches between thresholds from a discrete set to increase the unce…

Learning Near-Optimal Intrusion Responses Against Dynamic Attackers

2023-01-11 · Kim Hammar, Rolf Stadler

We study automated intrusion response and formulate the interaction between an attacker and a defender as an optimal stopping game where attack and defense strategies evolve through reinforcement learning and self-play. …