JALAPENO11/pii-inverter-bart-base

PII Model-Inversion Inverter — BART-base

Repo: JALAPENO11/pii-inverter-bart-base

This model is a model-inversion attack against a PII anonymisation system. It was trained to reverse the output of a BART-base anonymiser:

anonymised text → (inverter) → recovered original text

---

Training Details

Parameter	Value
Base model	facebook/bart-base
Checkpoint epoch	8
Global step	12479
Saved at	2026-04-06T01:42:04.473556
Train loss	0.3834
Eval loss	0.4518
Perplexity	1.57
Token accuracy	0.4206
ERR exact	0.2925
ERR partial	0.0282
Eval samples	1918

---

Evaluation Metrics

Attack B — Inverter Model (best checkpoint)

Metric	Value
ERR exact	0.2925 (29.2% entities recovered verbatim)
ERR partial	0.0282
Token accuracy	0.4206
Exact sentence match	0.1528
Corpus BLEU	0.6466

ERR by adversarial strategy

Strategy	Samples	ERR exact
S2_combinatorial_pii	424	0.1958
S3_paraphrase_consistency	261	0.4521
S4_rarity_spectrum	311	0.2990
S1_entity_consistency	556	0.2878
S6_edge_cases	186	0.3548
S5_cross_entity_correlation	180	0.2278

ERR by name rarity

Rarity	Samples	ERR exact
unknown	1051	0.2931
common	128	0.3750
rare	249	0.2088
very_rare	134	0.3134
medium	356	0.3118

---

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

tokenizer = AutoTokenizer.from_pretrained("JALAPENO11/pii-inverter-bart-base")
model     = AutoModelForSeq2SeqLM.from_pretrained("JALAPENO11/pii-inverter-bart-base")
model.eval()

anonymized = "Dear Ms. Anya Sharma, please update your account details."

inputs = tokenizer(anonymized, return_tensors="pt",
                   max_length=128, truncation=True)
with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=128, num_beams=4)
print(tokenizer.decode(out[0], skip_special_tokens=True))
# → "Dear Amyna Tharathip, please update your account details."

---

Disclaimer

This model is published for research purposes only to study the robustness of PII anonymisation systems. It should not be used to de-anonymise real personal data.

See attack_report.txt in the repo Files tab for the full evaluation report.