REVIEW 5 cited by
Large Language Models are Advanced Anonymizers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are currently lacking behind regulatory requirements and adversarial threats. In this work, we take two steps to bridge this gap: First, we present a new setting for evaluating anonymization in the face of adversarial LLM inferences, allowing for a natural measurement of anonymization performance while remedying some of the shortcomings of previous metrics. Then, within this setting, we develop a novel LLM-based adversarial anonymization framework leveraging the strong inferential capabilities of LLMs to inform our anonymization procedure. We conduct a comprehensive experimental evaluation of adversarial anonymization across 13 LLMs on real-world and synthetic online texts, comparing it against multiple baselines and industry-grade anonymizers. Our evaluation shows that adversarial anonymization outperforms current commercial anonymizers both in terms of the resulting utility and privacy. We support our findings with a human study (n=50) highlighting a strong and consistent human preference for LLM-anonymized texts.
Forward citations
Cited by 5 Pith papers
-
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
PromptPET selectively applies four obfuscation actions (including novel noising) via an OPRO-style rule optimizer to match single-action privacy-utility frontiers and outperform prior prompt-minimization methods on Wi...
-
Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
A retrieval-confused generation defense that swaps query comments with the most irrelevant paraphrased comments, reducing privacy attack success rates across eight LLMs.
-
Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution
The paper proposes integrating Unicode steganography into adversarial stylometry to undermine authorship attribution.
-
PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)
NER-based removal of person and location entities from resumes preserves occupancy-prediction accuracy on FairCVdb, and combined with a debiasing module yields gender-balanced shortlists.
-
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.
Discussion (0). Sign in to comment.