Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent

• URL: http://arxiv.org/abs/2407.21073v1
• Date: Mon, 29 Jul 2024 09:07:29 GMT
• Title: Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent
• Authors: Hetvi Waghela, Jaydip Sen, Sneha Rakshit,
• Abstract summary: Adrial attacks against deep learning models represent a major threat to the security and reliability of natural language processing systems. We propose a modification to the BERT-Attack framework, integrating Projected Gradient Descent (PGD) to enhance its effectiveness and robustness.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framework, integrating Projected Gradient Descent (PGD) to enhance its effectiveness and robustness. The original BERT-Attack, designed for generating adversarial examples against BERT-based models, suffers from limitations such as a fixed perturbation budget and a lack of consideration for semantic similarity. The proposed approach in this work, PGD-BERT-Attack, addresses these limitations by leveraging PGD to iteratively generate adversarial examples while ensuring both imperceptibility and semantic similarity to the original input. Extensive experiments are conducted to evaluate the performance of PGD-BERT-Attack compared to the original BERT-Attack and other baseline methods. The results demonstrate that PGD-BERT-Attack achieves higher success rates in causing misclassification while maintaining low perceptual changes. Furthermore, PGD-BERT-Attack produces adversarial instances that exhibit greater semantic resemblance to the initial input, enhancing their applicability in real-world scenarios. Overall, the proposed modification offers a more effective and robust approach to adversarial attacks on BERT-based models, thus contributing to the advancement of defense against attacks on NLP systems.

Related papers

• Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability [12.695100767905243]
  This study advances adversarial training by leveraging principles from Conformal Prediction.<n>We develop an adversarial attack method, termed OPSA (OPtimal Size Attack), designed to reduce the efficiency of conformal prediction.<n>We introduce OPSA-AT (Adversarial Training), a defense strategy that integrates OPSA within a novel conformal training paradigm.
  arXiv  Detail & Related papers  (2025-06-09T14:33:28Z)
• IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method [6.660834045805309]
  IM-BERT is a solution of Ordinary Differential Equations (ODEs)<n>We introduce a numerically robust IM-connection incorporating BERT's layers.<n>Compared to the original BERT, IM-BERT exhibits a performance improvement of approximately 8.3%p on the AdvGLUE dataset.
  arXiv  Detail & Related papers  (2025-05-11T07:54:33Z)
• DiffBreak: Breaking Diffusion-Based Purification with Adaptive Attacks [20.15955997832192]
  Diffusion-based purification (DBP) has emerged as a cornerstone defense against adversarial examples (AEs) We prove that adaptive gradient-based attacks nullify this foundational claim. We propose a novel adaptation of a recent optimization method against deepfake watermarking.
  arXiv  Detail & Related papers  (2024-11-25T17:30:32Z)
• The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks [90.52808174102157]
  In safety-critical applications such as medical imaging and autonomous driving, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks. A notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. This study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks.
  arXiv  Detail & Related papers  (2024-05-14T18:05:19Z)
• Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation [2.3371504588528635]
  This work studies sparse adversarial perturbations, including both unstructured and structured ones. We propose a framework based on a white-box PGD-like attack method named Sparse-PGD to effectively and efficiently generate such perturbations. We combine Sparse-PGD with a black-box attack to evaluate the models' robustness against unstructured and structured sparse adversarial perturbations.
  arXiv  Detail & Related papers  (2024-05-08T14:18:13Z)
• Improving Adversarial Training using Vulnerability-Aware Perturbation Budget [7.430861908931903]
  Adversarial Training (AT) effectively improves the robustness of Deep Neural Networks (DNNs) to adversarial attacks. We propose two simple, computationally cheap vulnerability-aware reweighting functions for assigning perturbation bounds to adversarial examples used for AT. Experimental results show that the proposed methods yield genuine improvements in the robustness of AT algorithms against various adversarial attacks.
  arXiv  Detail & Related papers  (2024-03-06T21:50:52Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off [107.35833747750446]
  adversarial examples can be crafted by adding imperceptible perturbations to legitimate documents. This vulnerability raises significant concerns about their reliability and hinders the widespread deployment of NRMs. In this study, we establish theoretical guarantees regarding the effectiveness-robustness trade-off in NRMs.
  arXiv  Detail & Related papers  (2023-12-16T05:38:39Z)
• LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack [11.764601181046496]
  Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. We propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process.
  arXiv  Detail & Related papers  (2023-07-04T07:00:37Z)
• IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks [45.81957796169348]
  Backdoor attacks are an insidious security threat against machine learning models. We introduce IMBERT, which uses either gradients or self-attention scores derived from victim models to self-defend against backdoor attacks. Our empirical studies demonstrate that IMBERT can effectively identify up to 98.5% of inserted triggers.
  arXiv  Detail & Related papers  (2023-05-25T22:08:57Z)
• In and Out-of-Domain Text Adversarial Robustness via Label Smoothing [64.66809713499576]
  We study the adversarial robustness provided by various label smoothing strategies in foundational models for diverse NLP tasks. Our experiments show that label smoothing significantly improves adversarial robustness in pre-trained models like BERT, against various popular attacks. We also analyze the relationship between prediction confidence and robustness, showing that label smoothing reduces over-confident errors on adversarial examples.
  arXiv  Detail & Related papers  (2022-12-20T14:06:50Z)
• BERT-ATTACK: Adversarial Attack Against BERT Using BERT [77.82947768158132]
  Adrial attacks for discrete data (such as texts) are more challenging than continuous data (such as images) We propose textbfBERT-Attack, a high-quality and effective method to generate adversarial samples. Our method outperforms state-of-the-art attack strategies in both success rate and perturb percentage.
  arXiv  Detail & Related papers  (2020-04-21T13:30:02Z)
• Adversarial Distributional Training for Robust Deep Learning [53.300984501078126]
  Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. Most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models.
  arXiv  Detail & Related papers  (2020-02-14T12:36:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.