Research Papers 论文研究 16h ago Updated 2h ago 更新于 2小时前 49

Making Open-Source Text LLM Watermarks Durable Against Merging 使开源文本大语言模型水印对合并具有耐久性

Introduces Merge-Adversarial Training, a novel adversarial training algorithm designed to embed watermarks into open-source LLM weights that survive subsequent model merging. Demonstrates significant performance gains over baselines, achieving up to +51 percentage points improvement in True Positive Rate at 1% False Positive Rate when using SLERP merging. Provides the first evaluation of OSM watermarks against realistic merge scenarios, including combining expert capabilities and preventing cata 提出 Merge-Adversarial Training 算法,首次实现开源大模型水印在模型合并后仍具鲁棒性。 针对 SLERP 等主流合并算法,该方法将水印检测的 TPR@1%FPR 提升高达 51 个百分点。 在增强水印耐久性的同时,有效保留了模型的下游任务能力,未造成性能显著退化。 构建了包含专家知识融合和防止灾难性遗忘等真实场景的水印评估基准。

65
Hot 热度
75
Quality 质量
70
Impact 影响力

Analysis 深度分析

TL;DR

  • Introduces Merge-Adversarial Training, a novel adversarial training algorithm designed to embed watermarks into open-source LLM weights that survive subsequent model merging.
  • Demonstrates significant performance gains over baselines, achieving up to +51 percentage points improvement in True Positive Rate at 1% False Positive Rate when using SLERP merging.
  • Provides the first evaluation of OSM watermarks against realistic merge scenarios, including combining expert capabilities and preventing catastrophic forgetting across three prominent merging algorithms.
  • Establishes adversarial training as a reliable method for enhancing watermark durability against post-training modifications without compromising downstream model capabilities.

Why It Matters

This research addresses a critical vulnerability in AI transparency and accountability: the fragility of watermarks when open-source models are fine-tuned or merged. As model merging becomes a standard practice for creating specialized experts from base models, ensuring that provenance tracking remains intact is essential for detecting misuse and maintaining trust in generated content.

Technical Details

  • Methodology: Proposes "Merge-Adversarial Training," which distills text watermarks into model weights while explicitly optimizing for robustness against various model merging techniques.
  • Benchmarking: Evaluates watermark durability against three prominent merging algorithms in realistic scenarios such as combining expert knowledge and mitigating catastrophic forgetting.
  • Performance Metrics: Reports substantial improvements in detection rates, specifically noting an average increase of +25 percentage points and up to +51 percentage points in TPR@1%FPR compared to existing baselines using SLERP.
  • Capability Preservation: Ensures that the integration of durable watermarks does not degrade the model's general downstream performance or utility.

Industry Insight

  • Security by Design: Developers integrating watermarks into open-source models must adopt adversarial training techniques rather than simple embedding methods to ensure longevity against common post-processing steps like merging.
  • Standardization Needs: The industry should consider establishing benchmarks for watermark robustness against specific post-training modifications, particularly model merging, to verify compliance and provenance claims.
  • Trust Infrastructure: As model merging proliferates, robust watermarking becomes a prerequisite for responsible AI deployment, enabling better traceability of AI-generated content across complex model ecosystems.

TL;DR

  • 提出 Merge-Adversarial Training 算法,首次实现开源大模型水印在模型合并后仍具鲁棒性。
  • 针对 SLERP 等主流合并算法,该方法将水印检测的 TPR@1%FPR 提升高达 51 个百分点。
  • 在增强水印耐久性的同时,有效保留了模型的下游任务能力,未造成性能显著退化。
  • 构建了包含专家知识融合和防止灾难性遗忘等真实场景的水印评估基准。

为什么值得看

随着开源大模型性能逼近 SOTA,模型合并成为微调与整合的关键手段,但现有水印极易被破坏。本研究解决了开源模型溯源在复杂后处理场景下的核心痛点,为 AI 内容治理提供了关键技术支撑。

技术解析

  • 核心方法:采用对抗训练(Adversarial Training)机制,在蒸馏水印到模型权重的过程中,模拟模型合并操作,使水印对合并扰动具有免疫力。
  • 性能指标:在 SLERP 合并策略下,相比基线方法,True Positive Rate (TPR) at 1% False Positive Rate (FPR) 平均提升 25pp,最高提升达 51pp。
  • 评估场景:首次在 realistic merge scenarios 下进行测试,涵盖结合专家能力、防止灾难性遗忘等常见用例,并对比了三种主流合并算法。
  • 能力保持:验证显示,经过该算法处理后的模型在常规下游任务中保持了原有的性能水平,证明了鲁棒性与可用性之间的平衡。

行业启示

  • 水印标准升级:未来的开源模型水印设计必须考虑后训练修改(如 LoRA 合并、模型集成)的影响,静态嵌入水印已不再足够。
  • 合规与溯源:随着模型合并技术的普及,建立抗合并的水印机制对于确保生成内容的可追溯性和版权保护至关重要。
  • 防御性开发趋势:对抗性训练不仅是攻击手段,也可用于增强模型属性的持久性,建议在模型发布前引入此类鲁棒性测试流程。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Open Source 开源 LLM 大模型 Security 安全 Research 科学研究