REVIEW 6 cited by
Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers
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
Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based language models to classify input texts. However, there is a lack of systematic study on how much private information can be inverted when publishing models. In this paper, we formulate \emph{Text Revealer} -- the first model inversion attack for text reconstruction against text classification with transformers. Our attacks faithfully reconstruct private texts included in training data with access to the target model. We leverage an external dataset and GPT-2 to generate the target domain-like fluent text, and then perturb its hidden state optimally with the feedback from the target model. Our extensive experiments demonstrate that our attacks are effective for datasets with different text lengths and can reconstruct private texts with accuracy.
Forward citations
Cited by 6 Pith papers
-
Model Inversion meets Cryptographic Fuzzy Extractors
A new attack, PIPE, defeats existing MRP and Facial-FE protections for face embeddings, and a new lattice-based fuzzy extractor, L2FE-Hash, is proposed and claimed to resist inversion.
-
Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models
An edge-cloud LLM serving scheme splits the final projection along the hidden dimension, keeps cache control and LoRA modules on-device, and reports 29-46% lower per-token latency and 56-67% lower downlink payloads th...
-
A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
The paper classifies model extraction attacks and defenses into attack, defense, and computing environment categories and surveys their current state.
-
A Survey on Model Extraction Attacks and Defenses for Large Language Models
A taxonomy of model extraction attacks and defenses for large language models, with proposed evaluation metrics and future research directions.
-
Securing AI Systems: A Guide to Known Attacks and Impacts
A practitioner-oriented review that organizes known adversarial attacks on predictive and generative AI systems into eleven types mapped to confidentiality, integrity, and availability impacts.
-
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.