Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training
Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable to simple perturbations and adversarial attacks. To build an effective defense against malicious perturbations, we view MGT detection from a threat modeling perspective, that is, analyzing the model's vulnerability from an adversary's point of view and exploring effective mitigations. To this end, we introduce an adversarial framework for training a robust MGT detector, named GREedy Adversary PromoTed DefendER (GREATER). The GREATER consists of two key components: an adversary GREATER-A and a detector GREATER-D. The GREATER-D learns to defend against the adversarial attack from GREATER-A and generalizes the defense to other attacks. GREATER-A identifies and perturbs the critical tokens in embedding space, along with greedy search and pruning to generate stealthy and disruptive adversarial examples. Besides, we update the GREATER-A and GREATER-D synchronously, encouraging the GREATER-D to generalize its defense to different attacks and varying attack intensities. Our experimental results across 10 text perturbation strategies and 6 adversarial attacks show that our GREATER-D reduces the Attack Success Rate (ASR) by 0.67% compared with SOTA defense methods while our GREATER-A is demonstrated to be more effective and efficient than SOTA attack approaches. Codes and dataset are available in https://github.com/Liyuuuu111/GREATER.
Code (1)
Tasks
Adversarial AttackText DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising
Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as perturbations in the observation space ma…
continuous-controlContinuous ControlDeep Reinforcement LearningDenoising+2Implementation Considerations for ACAS and Simulation Results
The Assisted Commercial Authentication Service (ACAS) is a semi-assisted signal authentication concept currently being defined for Galileo, based on the E6-C encrypted signal. Leveraging the assumption that the true E6-C…
Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference at…
BIG-bench Machine LearningInference AttackDefending Against Physically Realizable Attacks on Image Classification
We study the problem of defending deep neural network approaches for image classification from physically realizable attacks. First, we demonstrate that the two most scalable and effective methods for learning robust mod…
ClassificationGeneral Classificationimage-classificationImage ClassificationAdaptive Trust Consensus for Blockchain IoT: Comparing RL, DRL, and MARL Against Naive, Collusive, Adaptive, Byzantine, and Sleeper Attacks
Securing blockchain-enabled IoT networks against sophisticated adversarial attacks remains a critical challenge. This paper presents a trust-based delegated consensus framework integrating Fully Homomorphic Encryption (F…
Reinforcement LearningAdversarial Attack