One-Prompt Censorship Evasion via Generative Diffusion Models

• URL: http://arxiv.org/abs/2606.22717v1
• Date: Sun, 21 Jun 2026 23:28:58 GMT
• Title: One-Prompt Censorship Evasion via Generative Diffusion Models
• Abstract summary: FlowPaint is a novel framework for semantic image-to-image editing on network flows.<n>We introduce a novel generative framework that leverages the "world knowledge" of large diffusion models to automatically reshape censored traffic into benign patterns.
• Score: 9.151383048946803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The escalating arms race between Internet censorship and evasion has driven censors to evolve from static rule-based filtering to sophisticated deep learning-based traffic analysis. While recent automated evasion tools have attempted to counter this by leveraging stochastic search and programmable heuristics, they continue to suffer from insufficient evasion robustness across diverse censorship modalities and poor usability due to complex, mechanism-specific configurations that require manual fitness tuning or domain-specific languages. In this paper, we propose a paradigm shift that reframes censorship evasion as a semantic image-to-image editing task, allowing users to execute it with a single prompt. We introduce FlowPaint, a novel generative framework that leverages the "world knowledge" of large diffusion models to automatically reshape censored traffic into benign patterns. FlowPaint utilizes an instruction-tuned diffusion architecture to perform semantic editing on network flows. Evaluations against both industrial-grade rule-based middleboxes and learning-based classifiers demonstrate that FlowPaint outperforms existing censorship evasion baselines, enabling users to counter diverse censorship paradigms solely by varying natural language instructions

Related papers

• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents [0.09786690381850356]
  RIZZ is a continual adaptation framework for compound language-model systems.<n>It learns entirely through verifier-gated memory, routing, and prompt compilation.<n>RIZZ targets the regime where adaptation must occur online under context budgets.
  arXiv  Detail & Related papers  (2026-06-02T14:40:01Z)
• Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters [17.105244809853907]
  We show that modern text-to-image models remain vulnerable to low-effort jailbreak attacks that require only natural language prompts.<n>We present a systematic study of prompt-based strategies that bypass safety filters without model access, optimization, or adversarial training.<n>We evaluate these attacks across several state-of-the-art text-to-image systems and demonstrate that simple linguistic modifications can reliably evade existing safeguards.
  arXiv  Detail & Related papers  (2026-04-02T10:51:58Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning [76.2503352325492]
  ControlThinker is a novel framework that employs a "comprehend-then-generate" paradigm.<n>Latent semantics from control images are mined to enrich text prompts.<n>This enriched semantic understanding then seamlessly aids in image generation without the need for additional complex modifications.
  arXiv  Detail & Related papers  (2025-06-04T05:56:19Z)
• Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts [68.48103545146127]
  This paper proposes a novel framework for unsupervised exploration of diffusion latent spaces. We directly leverage natural language prompts and image captions to map latent directions. Our method provides a more scalable and interpretable understanding of the semantic knowledge encoded within diffusion models.
  arXiv  Detail & Related papers  (2024-10-25T21:44:51Z)
• Instruct2Attack: Language-Guided Semantic Adversarial Attacks [76.83548867066561]
  Instruct2Attack (I2A) is a language-guided semantic attack that generates meaningful perturbations according to free-form language instructions. We make use of state-of-the-art latent diffusion models, where we adversarially guide the reverse diffusion process to search for an adversarial latent code conditioned on the input image and text instruction. We show that I2A can successfully break state-of-the-art deep neural networks even under strong adversarial defenses.
  arXiv  Detail & Related papers  (2023-11-27T05:35:49Z)
• Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning [8.788469979827484]
  Recent advances in machine learning enable detecting a range of anti-censorship systems by learning distinct statistical patterns hidden in traffic flows. In this paper, we formulate a practical adversarial attack strategy against flow classifiers as a method for circumventing censorship. We show that Amoeba can effectively shape adversarial flows that have on average 94% attack success rate against a range of ML algorithms.
  arXiv  Detail & Related papers  (2023-10-31T14:01:24Z)
• Augmenting Rule-based DNS Censorship Detection at Scale with Machine Learning [38.00013408742201]
  Censorship of the domain name system (DNS) is a key mechanism used across different countries. In this paper, we explore how machine learning (ML) models can help streamline the detection process. We find that unsupervised models, trained solely on uncensored instances, can identify new instances and variations of censorship missed by existing probes.
  arXiv  Detail & Related papers  (2023-02-03T23:36:30Z)
• Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word Camouflage [64.78260098263489]
  Twisting and camouflaging keywords are among the most used techniques to evade platform content moderation systems. This article contributes significantly to countering malicious information by developing multilingual tools to simulate and detect new methods of evasion of content.
  arXiv  Detail & Related papers  (2022-12-27T16:08:49Z)

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.