Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
원문 초록
Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and some recently deployed defenses -- focus on "verbatim memorization", defined as a model generation that exactly matches a substring from the training set. We argue that verbatim memorization definitions are too restrictive and fail to capture more subtle forms of memorization. Specifically, we design and implement an efficient defense that perfectly prevents all verbatim memorization. And yet, we demonstrate that this "perfect" filter does not prevent the leakage of training data. Indeed, it is easily circumvented by plausible and minimally modified "style-transfer" prompts -- and in some cases even the non-modified original prompts -- to extract memorized information. We conclude by discussing potential alternative definitions and why defining memorization is a difficult yet crucial open question for neural language models.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledge
LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data
SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
Diffusion models under low-noise regime
토론
이 논문과 연결된 포럼 글이 아직 없습니다.