Amplifying Membership Exposure via Data Poisoning
As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction. In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples. To this end, we demonstrate a set of data poisoning attacks to amplify the membership exposure of the targeted class. We first propose a generic dirty-label attack for supervised classification algorithms. We then propose an optimization-based clean-label attack in the transfer learning scenario, whereby the poisoning samples are correctly labeled and look "natural" to evade human moderation. We extensively evaluate our attacks on computer vision benchmarks. Our results show that the proposed attacks can substantially increase the membership inference precision with minimum overall test-time model performance degradation. To mitigate the potential negative impacts of our attacks, we also investigate feasible countermeasures.
Code (1)
Tasks
Data PoisoningOverall - TestTransfer LearningSimilar Papers 제목 키워드 기반
MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning
Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g., artists) urgently need to determine whether their …
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to ampl…
MemorizationWhat Really is a Member? Discrediting Membership Inference via Poisoning
Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often fail under the strict definition of memb…
Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs
Large language models are increasingly used for code generation and debugging, but their outputs can still contain bugs, that originate from training data. Distinguishing whether an LLM prefers correct code, or a familia…
Code GenerationCode CompletionChameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inferen…
Data Poisoning