LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets

• URL: http://arxiv.org/abs/2607.14101v1
• Date: Tue, 05 May 2026 13:40:10 GMT
• Title: LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets
• Abstract summary: We propose a sampling-based method called LBA to generate high-quality adversarial texts with low query budgets.<n>In experiments on six language models, LBA significantly outperforms state-of-the-art baselines on all evaluation metrics.
• Score: 41.38996351903662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating high-quality adversarial texts with low query budgets remains a challenging problem in the hard-label scenario. Most existing approaches rely on greedy algorithms, where one position in the text is selected for substitution, followed by the substitutions of other positions. This local search approach may fail to discover high-quality adversarial examples and often leads to excessive query costs. Ideally, an optimal adversarial sample would consider all possible position combinations in the text, but exhaustive search is computationally impractical. To address this challenge, we propose a sampling-based method called LBA, which constructs an approximate distribution of high-quality adversarial examples by integrating both prior and posterior knowledge, and utilizes this distribution for sampling. As sampling progresses, posterior knowledge updates the approximate distribution, which in turn guides more effective sampling. Extensive experiments on six language models, ranging from small-scale to large-scale architectures across four datasets, demonstrate that LBA significantly outperforms state-of-the-art baselines on all evaluation metrics. Additionally, LLM-based assessment indicates that LBA generates more semantically preserved and comprehensible adversarial texts.

Related papers

• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• Context Attribution with Multi-Armed Bandit Optimization [11.715006981206844]
  We propose a novel framework that formulates context attribution as a multi-armed bandit (CMAB) problem.<n>We employ Combinatorial Thompson Sampling (CTS) to efficiently explore the exponentially large space of context subsets under a limited query budget.<n>Our method defines a reward function based on normalized token likelihoods, capturing how well a subset of segments supports the original model response.
  arXiv  Detail & Related papers  (2025-06-24T19:47:27Z)
• The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection [2.4829769683482437]
  Scene text detection methods often fail to replicate such success in real-world scenarios.<n>We uncover two key factors contributing to this discrepancy through extensive experiments.<n>We propose a Long-Tailed Benchmark (LTB) to evaluate ability to handle a diverse range of long-tailed challenges.
  arXiv  Detail & Related papers  (2025-05-21T15:26:46Z)
• Nearly Optimal Sample Complexity for Learning with Label Proportions [54.67830198790247]
  We investigate Learning from Label Proportions (LLP), a partial information setting where examples in a training set are grouped into bags.<n>Despite the partial observability, the goal is still to achieve small regret at the level of individual examples.<n>We give results on the sample complexity of LLP under square loss, showing that our sample complexity is essentially optimal.
  arXiv  Detail & Related papers  (2025-05-08T15:45:23Z)
• Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation [60.493180081319785]
  We propose a systematic way to estimate the capacity of a truncation sampling method by considering the trade-off between diversity and risk at each decoding step.<n>Our work offers a comprehensive comparison of existing truncation sampling methods and serves as a practical user guideline for their parameter selection.
  arXiv  Detail & Related papers  (2024-08-24T14:14:32Z)
• Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs [0.41436032949434404]
  We introduce paired completion', a novel approach to detect contrasting frames using minimal examples.<n>We demonstrate that paired completion is a cost-efficient, low-bias alternative to both prompt-based and embedding-based methods.
  arXiv  Detail & Related papers  (2024-08-19T07:14:15Z)
• Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models [24.085614720512744]
  This study shows that large language models (LLMs) are vulnerable to changes in the number and arrangement of options in text classification. Key bottleneck arises from ambiguous decision boundaries and inherent biases towards specific tokens and positions. Our approach is grounded in the empirical observation that pairwise comparisons can effectively alleviate boundary ambiguity and inherent bias.
  arXiv  Detail & Related papers  (2024-06-11T06:53:19Z)
• Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model [14.98695074168234]
  We propose a new method to detect machine-generated text, especially from large language models (LLMs) We use a Bayesian surrogate model, which allows us to select typical samples based on Bayesian uncertainty and interpolate scores from typical samples to other samples, to improve query efficiency. Empirical results demonstrate that our method significantly outperforms existing approaches under a low query budget.
  arXiv  Detail & Related papers  (2023-05-26T04:23:10Z)
• Finding Support Examples for In-Context Learning [73.90376920653507]
  We propose LENS, a fiLter-thEN-Search method to tackle this challenge in two stages. First we filter the dataset to obtain informative in-context examples individually. Then we propose diversity-guided example search which iteratively refines and evaluates the selected example permutations.
  arXiv  Detail & Related papers  (2023-02-27T06:32:45Z)
• The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime [52.38455827779212]
  We propose a novel technique for analyzing adaptive sampling called the em Simulator. We prove the first instance-based lower bounds the top-k problem which incorporate the appropriate log-factors. Our new analysis inspires a simple and near-optimal for the best-arm and top-k identification, the first em practical of its kind for the latter problem.
  arXiv  Detail & Related papers  (2017-02-16T23:42:02Z)

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.