Unitary Multi-Margin BERT for Robust Natural Language Processing

• URL: http://arxiv.org/abs/2410.12759v1
• Date: Wed, 16 Oct 2024 17:30:58 GMT
• Title: Unitary Multi-Margin BERT for Robust Natural Language Processing
• Authors: Hao-Yuan Chang, Kang L. Wang,
• Abstract summary: Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this paper reports a novel, universal technique that drastically improves the robustness of Bidirectional Representations from Transformers (BERT) by combining the unitary weights with the multi-margin loss. Our model, the unitary multi-margin BERT (UniBERT), boosts post-attack classification accuracies significantly by 5.3% to 73.8% while maintaining competitive pre-attack accuracies.
• Score: 0.0
• License:
• Abstract: Recent developments in adversarial attacks on deep learning leave many mission-critical natural language processing (NLP) systems at risk of exploitation. To address the lack of computationally efficient adversarial defense methods, this paper reports a novel, universal technique that drastically improves the robustness of Bidirectional Encoder Representations from Transformers (BERT) by combining the unitary weights with the multi-margin loss. We discover that the marriage of these two simple ideas amplifies the protection against malicious interference. Our model, the unitary multi-margin BERT (UniBERT), boosts post-attack classification accuracies significantly by 5.3% to 73.8% while maintaining competitive pre-attack accuracies. Furthermore, the pre-attack and post-attack accuracy tradeoff can be adjusted via a single scalar parameter to best fit the design requirements for the target applications.

Related papers

• Improved Generation of Adversarial Examples Against Safety-aligned LLMs [72.38072942860309]
  Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks. We show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench.
  arXiv  Detail & Related papers  (2024-05-28T06:10:12Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks [62.036798488144306]
  Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. We propose an attack-agnostic defense method named Meta Invariance Defense (MID) We show that MID simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration.
  arXiv  Detail & Related papers  (2024-04-04T10:10:38Z)
• Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge [17.3048898399324]
  democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. backdoor attacks, where hidden malicious behaviors are triggered by specific inputs, compromising natural language processing (NLP) system integrity and reliability. This paper suggests that merging a backdoored model with other homogeneous models can significantly remediate backdoor vulnerabilities.
  arXiv  Detail & Related papers  (2024-02-29T16:37:08Z)
• Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks [47.21491911505409]
  Adrial training serves as one of the most popular and effective methods to defend against adversarial perturbations. We propose a novel multi-perturbation adversarial training framework, parameter-saving adversarial training (PSAT), to reinforce multi-perturbation robustness.
  arXiv  Detail & Related papers  (2023-09-28T07:16:02Z)
• Backdoor Pre-trained Models Can Transfer to All [33.720258110911274]
  We propose a new approach to map the inputs containing triggers directly to a predefined output representation of pre-trained NLP models. In light of the unique properties of triggers in NLP, we propose two new metrics to measure the performance of backdoor attacks.
  arXiv  Detail & Related papers  (2021-10-30T07:11:24Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)
• A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks [7.943024117353317]
  We develop a lightweight defense method that can efficiently invalidate full whitebox adversarial attacks with the compatibility of real-life constraints. Our model can withstand advanced adaptive attack, namely BPDA with 50 rounds, and still helps the target model maintain an accuracy around 80 %, meanwhile constraining the attack success rate to almost zero.
  arXiv  Detail & Related papers  (2020-07-30T08:06:53Z)
• Robust Encodings: A Framework for Combating Adversarial Typos [85.70270979772388]
  NLP systems are easily fooled by small perturbations of inputs. Existing procedures to defend against such perturbations provide guaranteed robustness to worst-case attacks. We introduce robust encodings (RobEn) that confer guaranteed robustness without making compromises on model architecture.
  arXiv  Detail & Related papers  (2020-05-04T01:28:18Z)
• 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)

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.