Thieves on Sesame Street! Model Extraction of BERT-based APIs
Reviewed by Pithpith:F4WT5YRFopen to challenge →
read the original abstract
We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model. Assuming that both the adversary and victim model fine-tune a large pretrained language model such as BERT (Devlin et al. 2019), we show that the adversary does not need any real training data to successfully mount the attack. In fact, the attacker need not even use grammatical or semantically meaningful queries: we show that random sequences of words coupled with task-specific heuristics form effective queries for model extraction on a diverse set of NLP tasks, including natural language inference and question answering. Our work thus highlights an exploit only made feasible by the shift towards transfer learning methods within the NLP community: for a query budget of a few hundred dollars, an attacker can extract a model that performs only slightly worse than the victim model. Finally, we study two defense strategies against model extraction---membership classification and API watermarking---which while successful against naive adversaries, are ineffective against more sophisticated ones.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Data Provenance for Image Auto-Regressive Generation
A post-hoc detection framework exploits generation-induced patterns in autoregressive image outputs to enable provenance tracing across multiple IAR models without altering the generation process.
-
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
Empirical benchmarks show distribution similarity between adaptation and pretraining data increases practical privacy leakage in DP-adapted LLMs at fixed theoretical guarantees, with LoRA providing strongest protectio...
-
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
RECAST reconstructs black-box models under limited data by treating counterfactuals as class samples within a Wasserstein geometry framework to preserve surrogate fidelity without online access.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.