CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models

• URL: http://arxiv.org/abs/2406.01873v2
• Date: Wed, 5 Jun 2024 15:53:01 GMT
• Title: CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
• Authors: Qian Lou, Xin Liang, Jiaqi Xue, Yancheng Zhang, Rui Xie, Mengxin Zheng,
• Abstract summary: Existing certified robustness based on random smoothing has shown considerable promise in certifying the input-specific text perturbations. A naive method is to simply increase the masking ratio and the likelihood of masking attack tokens, but it leads to a significant reduction in both certified accuracy and the certified radius. We introduce a novel approach, designed to identify a superior prompt that maintains higher certified accuracy under extensive masking.
• Score: 12.386141652094999
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: It is imperative to ensure the stability of every prediction made by a language model; that is, a language's prediction should remain consistent despite minor input variations, like word substitutions. In this paper, we investigate the problem of certifying a language model's robustness against Universal Text Perturbations (UTPs), which have been widely used in universal adversarial attacks and backdoor attacks. Existing certified robustness based on random smoothing has shown considerable promise in certifying the input-specific text perturbations (ISTPs), operating under the assumption that any random alteration of a sample's clean or adversarial words would negate the impact of sample-wise perturbations. However, with UTPs, masking only the adversarial words can eliminate the attack. A naive method is to simply increase the masking ratio and the likelihood of masking attack tokens, but it leads to a significant reduction in both certified accuracy and the certified radius due to input corruption by extensive masking. To solve this challenge, we introduce a novel approach, the superior prompt search method, designed to identify a superior prompt that maintains higher certified accuracy under extensive masking. Additionally, we theoretically motivate why ensembles are a particularly suitable choice as base prompts for random smoothing. The method is denoted by superior prompt ensembling technique. We also empirically confirm this technique, obtaining state-of-the-art results in multiple settings. These methodologies, for the first time, enable high certified accuracy against both UTPs and ISTPs. The source code of CR-UTP is available at \url {https://github.com/UCFML-Research/CR-UTP}.

Related papers

• MaskPure: Improving Defense Against Text Adversaries with Stochastic Purification [7.136205674624813]
  In computer vision settings, the noising and de-noising process has proven useful for purifying input images. Some initial work has explored the use of random noising and de-noising to mitigate adversarial attacks in an NLP setting. We extend upon methods of input purification text that are inspired by diffusion processes. Our novel method, MaskPure, exceeds or matches robustness compared to other contemporary defenses.
  arXiv  Detail & Related papers  (2024-06-18T21:27:13Z)
• Are AI-Generated Text Detectors Robust to Adversarial Perturbations? [9.001160538237372]
  Current detectors for AI-generated text (AIGT) lack robustness against adversarial perturbations. This paper investigates the robustness of existing AIGT detection methods and introduces a novel detector, the Siamese Calibrated Reconstruction Network (SCRN) The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations.
  arXiv  Detail & Related papers  (2024-06-03T10:21:48Z)
• Provably Secure Disambiguating Neural Linguistic Steganography [66.30965740387047]
  The segmentation ambiguity problem, which arises when using language models based on subwords, leads to occasional decoding failures. We propose a novel secure disambiguation method named SyncPool, which effectively addresses the segmentation ambiguity problem. SyncPool does not change the size of the candidate pool or the distribution of tokens and thus is applicable to provably secure language steganography methods.
  arXiv  Detail & Related papers  (2024-03-26T09:25:57Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks [39.51297217854375]
  We propose Text-CRS, a certified robustness framework for natural language processing (NLP) based on randomized smoothing. We show that Text-CRS can address all four different word-level adversarial operations and achieve a significant accuracy improvement. We also provide the first benchmark on certified accuracy and radius of four word-level operations, besides outperforming the state-of-the-art certification against synonym substitution attacks.
  arXiv  Detail & Related papers  (2023-07-31T13:08:16Z)
• Adaptive Shrink-Mask for Text Detection [91.34459257409104]
  Existing real-time text detectors reconstruct text contours by shrink-masks directly. The dependence on predicted shrink-masks leads to unstable detection results. Super-pixel Window (SPW) is designed to supervise the network.
  arXiv  Detail & Related papers  (2021-11-18T07:38:57Z)
• Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice [42.490810188180546]
  adversarial word substitution is one of the most challenging textual adversarial attack methods. This paper presents a compact and performance-preserved framework, Anomaly Detection with Frequency-Aware Randomization (ADFAR) We show that ADFAR significantly outperforms those newly proposed defense methods over various tasks with much higher inference speed.
  arXiv  Detail & Related papers  (2021-05-30T14:24:53Z)
• Towards Variable-Length Textual Adversarial Attacks [68.27995111870712]
  It is non-trivial to conduct textual adversarial attacks on natural language processing tasks due to the discreteness of data. In this paper, we propose variable-length textual adversarial attacks(VL-Attack) Our method can achieve $33.18$ BLEU score on IWSLT14 German-English translation, achieving an improvement of $1.47$ over the baseline model.
  arXiv  Detail & Related papers  (2021-04-16T14:37:27Z)
• MASKER: Masked Keyword Regularization for Reliable Text Classification [73.90326322794803]
  We propose a fine-tuning method, coined masked keyword regularization (MASKER), that facilitates context-based prediction. MASKER regularizes the model to reconstruct the keywords from the rest of the words and make low-confidence predictions without enough context. We demonstrate that MASKER improves OOD detection and cross-domain generalization without degrading classification accuracy.
  arXiv  Detail & Related papers  (2020-12-17T04:54:16Z)
• 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.