Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution
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.
Code (1)
Tasks
BenchmarkingSimilar Papers 제목 키워드 기반
A Framework for Enhancing Deep Neural Networks Against Adversarial Malware
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 DetectionThe Path To Autonomous Cyber Defense
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
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+2A Bayesian Nash equilibrium-based moving target defense against stealthy sensor attacks
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
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. …