SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space

Viktoriia Zinkovich, Anton Antonov, Andrei Spiridonov, Denis Shepelev, Andrey Moskalenko, Daria Pugacheva, Elena Tutubalina, Andrey Kuznetsov, Vlad Shakhuro

TL;DR

This paper introduces SPARTA, a novel black-box adversarial paraphrasing method that exposes the fragility of reasoning segmentation models. By optimizing prompts within the continuous latent space of a text autoencoder using reinforcement learning, SPARTA generates grammatically correct, semantically equivalent queries that severely degrade model performance, outperforming previous text attacks by up to 2×.

What Problem Does This Paper Address?

Multimodal Large Language Models (MLLMs) have made massive strides in vision-language tasks like reasoning segmentation—where a model must output a precise binary segmentation mask based on an implicit, complex text query (e.g., "What might the young girl be using to eat her dessert?").

While previous robustness research heavily focused on perturbing the visual input (like adding pixel noise), the textual input has remained largely underexplored. In real-world applications, users express the same intent in countless different ways. A robust model should produce the same segmentation mask regardless of how a prompt is paraphrased. This paper tackles the challenge of adversarial paraphrasing: generating fluent, grammatically correct text variations that preserve the original meaning but completely break the segmentation model's performance.

Methods

To circumvent the discrete optimization problem of text tokens—which often causes white-box gradient attacks to output ungrammatical gibberish—the authors developed SPARTA (Sentence-level Perturbation Adversarial Text Attack).

Example of an adversarial paraphrase generated by SPARTA

Key components of the method include:

  • Latent Sentence Space Exploration: SPARTA maps the input query into a continuous, low-dimensional semantic latent space using a pretrained text autoencoder called SONAR (a 1B-parameter multilingual model).
  • Reinforcement Learning Optimization: Using Proximal Policy Optimization (PPO), SPARTA learns a stochastic policy to perturb the latent vector.
  • Targeted Reward Function: The policy is rewarded for minimizing the Intersection over Union (IoU) between the predicted mask and the ground truth (maximizing degradation) while maintaining a regularization penalty to keep the perturbed vector close to the original embedding space.
  • Rigorous Post-Hoc Filtering: Because automated evaluation of paraphrases is notoriously difficult, the authors designed a hybrid validation protocol. It combines an LLM grader (Qwen3-32B) with regular expressions (to enforce capitalization and punctuation consistency) and cosine similarity filtering (via Qwen3-Embedding-8B) to ensure the generated text is a valid paraphrase.

Datasets

The authors evaluated their approach on two primary reasoning segmentation benchmarks:

  1. ReasonSeg: The standard benchmark dataset for evaluating reasoning-based segmentation tasks.
  2. LLMSeg-40k: A newer, larger-scale dataset collected via ChatGPT-4, featuring longer queries (averaging 15.2 words) and significantly higher linguistic complexity.

Due to computational constraints, a subset of 300 samples from each dataset was utilized for the evaluation.

Key Insights and Ideas

  • Latent Space vs. Token Substitution: Operating in a continuous latent space allows the attack to modify sentence structure globally rather than relying on simple word-swapping or character edits, leading to much more natural-sounding paraphrases.
  • The Length Confound in Embeddings: During their analysis of the SONAR autoencoder, the authors discovered that a single dimension (dim 654) strongly correlates with sentence length ($r = -0.956$). This means text autoencoders explicitly encode sequence length in a disentangled coordinate, which can inadvertently confound semantic similarity metrics if sentences vary in length.
  • LLM Evaluation Blindspots: The study revealed that modern LLMs are overly permissive when judging paraphrases, often rating overly verbose, riddle-like sentences as valid. This highlighted the necessity of their hybrid evaluation protocol (LLM + RegExp + Cosine Similarity).

Key Results

SPARTA demonstrated a remarkable ability to expose vulnerabilities across three state-of-the-art reasoning segmentation models (LISA, LISA++, and GSVA).

Success rate as a function of IoU-drop threshold
  • Performance Boost: SPARTA consistently outperformed competitive baselines (like GBDA and PAIR), achieving up to a 2× improvement in attack success rate metrics on the LLMSeg-40k dataset.
  • Model Vulnerability: When combining all baselines into a "unified attack," the success rate reached up to 68% at a 10% relative IoU drop threshold. This proves that current reasoning segmentation models remain highly vulnerable to well-crafted, semantic-preserving text adjustments.
  • Capacity and Robustness: Larger models (e.g., LISA 13B vs. 7B) consistently demonstrated higher resistance to adversarial paraphrasing, suggesting that scaling model capacity inherently aids textual robustness.

Limitations and Future Work

Despite its success, the authors note a few limitations:

  • Post-Hoc Validity: SPARTA does not guarantee that a valid paraphrase is generated during the optimization loop; invalid or unnatural prompts must be filtered out after generation. Future work could integrate validity constraints directly into the RL training process.
  • Human Naturalness: Some generated text variations can still sound slightly unnatural to human users due to inherent limitations in current text autoencoders.
  • Lack of Defenses: The paper focuses exclusively on the attack vector. Developing robust defense strategies and training techniques to mitigate these paraphrasing vulnerabilities remains an open and critical next step.

Summary updated

Abstract

Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation, where models generate segmentation masks based on textual queries. While prior work has primarily focused on perturbing image inputs, semantically equivalent textual paraphrases-crucial in real-world applications where users express the same intent in varied ways-remain underexplored. To address this gap, we introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance. To evaluate the quality of adversarial paraphrases, we develop a comprehensive automatic evaluation protocol validated with human studies. Furthermore, we introduce SPARTA-a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder, guided by reinforcement learning. SPARTA achieves significantly higher success rates, outperforming prior methods by up to 2x on both the ReasonSeg and LLMSeg-40k datasets. We use SPARTA and competitive baselines to assess the robustness of advanced reasoning segmentation models. We reveal that they remain vulnerable to adversarial paraphrasing-even under strict semantic and grammatical constraints. All code and data will be released publicly upon acceptance.
BibTeX
@inproceedings{zinkovich2026sparta,
  author = {Viktoriia Zinkovich and Anton Antonov and Andrei Spiridonov and Denis Shepelev and Andrey Moskalenko and Daria Pugacheva and Elena Tutubalina and Andrey Kuznetsov and Vlad Shakhuro},
  title = {{SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space}},
  booktitle = {EACL (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.126},
}
Figure