Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography

• URL: http://arxiv.org/abs/2510.06565v1
• Date: Wed, 08 Oct 2025 01:32:59 GMT
• Title: Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography
• Abstract summary: Auto-Stega is a framework for self-evolving steganographic strategies.<n>It generates, evaluating, summarizing, and updating strategies at inference time.<n>To handle high embedding rates, we introduce PC-DNTE, a plug-and-play algorithm.
• Score: 21.817549738509346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid progress of LLMs, high quality generative text has become widely available as a cover for text steganography. However, prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency, imperceptibility, and security, particularly at high embedding rates. Accordingly, we propose Auto-Stega, an agent-driven self-evolving framework that is the first to realize self-evolving steganographic strategies by automatically discovering, composing, and adapting strategies at inference time; the framework operates as a closed loop of generating, evaluating, summarizing, and updating that continually curates a structured strategy library and adapts across corpora, styles, and task constraints. A decoding LLM recovers the information under the shared strategy. To handle high embedding rates, we introduce PC-DNTE, a plug-and-play algorithm that maintains alignment with the base model's conditional distribution at high embedding rates, preserving imperceptibility while enhancing security. Experimental results demonstrate that at higher embedding rates Auto-Stega achieves superior performance with gains of 42.2\% in perplexity and 1.6\% in anti-steganalysis performance over SOTA methods.

Related papers

• Code-Level Cost Function Generation for Spatial Image Steganography Using RAG-Enhanced Large Language Models [7.391239808920929]
  We propose a novel evolutionary system focused on exploiting Retrieval-Augmented Generation (RAG) enhanced language models.<n>This system incorporates a Self Evolving RAG (SE-RAG) module, wherein a Code Semantic Signature (CSS) translates procedural code into aligned queries.<n>Experiments on the BOSSBase and BOWS2 datasets demonstrate that the proposed framework consistently achieves higher steganographic security than existing automatically designed methods.
  arXiv  Detail & Related papers  (2026-07-07T05:58:33Z)
• Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning [76.93011742289768]
  Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories.<n>This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills.<n>We propose Strategy-Guided Policy Optimization, which replaces instance-level trajectory imitation with reusable strategy distillation.
  arXiv  Detail & Related papers  (2026-06-23T02:14:12Z)
• StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction [76.50439715778869]
  StraTA is a framework that introduces an explicit trajectory-level strategy into agentic reinforcement learning.<n>Experiments on ALFWorld, WebShop, and SciWorld show that StraTA consistently improves both sample efficiency and final performance.
  arXiv  Detail & Related papers  (2026-05-07T17:51:16Z)
• AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration [49.050688065974605]
  Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models.<n>We propose AutoMIA, an agentic framework that reformulates membership inference as an automated process of self-exploration and strategy evolution.
  arXiv  Detail & Related papers  (2026-04-01T15:17:45Z)
• Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text [0.4199844472131922]
  H-TechniqueRAG is a novel hierarchical RAG framework that injects this tactic-technique taxonomy as a strong inductive bias to achieve highly efficient and accurate annotation.<n>We show that H-TechniqueRAG not only outperforms the state-of-the-art TechniqueRAG by 3.8% in F1 score, but also achieves a 62.4% reduction in inference latency and a 60% decrease in LLM API calls.
  arXiv  Detail & Related papers  (2026-03-24T05:21:46Z)
• Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation [48.88299242238335]
  Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models.<n>We propose MLLMEmbed-ReID, a unified framework based on a powerful cloud-edge architecture.
  arXiv  Detail & Related papers  (2026-02-13T13:48:08Z)
• Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging [0.0]
  We provide a "task space" characterization of the MITRE ATT&CK text tagging task.<n>We construct our own multi-label hierarchical classification models for the text tagging task.<n>Our models meet or surpass state-of-the-art performance while relying only on classical machine learning methods.
  arXiv  Detail & Related papers  (2026-01-21T00:41:34Z)
• Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization [51.12422886183246]
  Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks.<n>Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the dynamic interplay between evolving threats and safeguards in real-world web contexts.<n>We propose ACE-Safety, a novel framework that jointly optimize attack and defense models by seamlessly integrating two key innovative procedures.
  arXiv  Detail & Related papers  (2025-11-24T15:23:41Z)
• AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling [54.47844626555395]
  AutoDAN-Turbo employs a lifelong learning agent to build a rich library of attack strategies from scratch.<n>While highly effective, its test-time generation process involves sampling a strategy and generating a single corresponding attack prompt.<n>We propose to further improve the attack performance of AutoDAN-Turbo through test-time scaling.
  arXiv  Detail & Related papers  (2025-10-06T21:16:09Z)
• Continuous-Time Reinforcement Learning for Asset-Liability Management [0.0]
  This paper proposes a novel approach for Asset-Liability Management (ALM) by employing continuous-time Reinforcement Learning (RL)<n>We develop a model-free, policy gradient-based soft actor-critic algorithm tailored to ALM for dynamically synchronizing assets and liabilities.<n>Our empirical study evaluates this approach against two enhanced traditional financial strategies, a model-based continuous-time RL method, and three state-of-the-art RL algorithms.
  arXiv  Detail & Related papers  (2025-09-27T12:36:51Z)
• SAGE: Strategy-Adaptive Generation Engine for Query Rewriting [8.941793732446856]
  We introduce the Strategy-Adaptive Generation Engine (SAGE), which operationalizes expert-crafted strategies in an reinforcement learning framework.<n>SAGE achieves new state-of-the-art NDCG@10 results, but also uncovers a compelling emergent behavior.<n>Our findings demonstrate that strategy-guided RL, enhanced with nuanced reward shaping, offers a scalable, efficient, and more interpretable paradigm for developing the next generation of robust information retrieval systems.
  arXiv  Detail & Related papers  (2025-06-24T16:50:51Z)
• Generative Auto-Bidding with Value-Guided Explorations [47.71346722705783]
  This paper introduces a novel offline Generative Auto-bidding framework with Value-Guided Explorations (GAVE)<n> Experimental results on two offline datasets and real-world deployments demonstrate that GAVE outperforms state-of-the-art baselines in both offline evaluations and online A/B tests.
  arXiv  Detail & Related papers  (2025-04-20T12:28:49Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis [20.503153899462323]
  We propose a framework for semi-supervised sentiment analysis.<n>We introduce two prompting strategies to semantically enhance unlabeled text.<n> Experiments show our method achieves remarkable performance over prior semi-supervised methods.
  arXiv  Detail & Related papers  (2025-01-29T12:03:11Z)
• Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models [62.12822290276912]
  Auto-RT is a reinforcement learning framework that automatically explores and optimize complex attack strategies.<n>By significantly improving exploration efficiency and automatically optimizing attack strategies, Auto-RT detects a boarder range of vulnerabilities, achieving a faster detection speed and 16.63% higher success rates compared to existing methods.
  arXiv  Detail & Related papers  (2025-01-03T14:30:14Z)

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.