Upload 11 files

app.py

@@ -0,0 +1,36 @@
+import torch
+from transformers import RobertaTokenizerFast, RobertaForSequenceClassification
+from peft import PeftModel, PeftConfig
+import gradio as gr
+
+def predict_phishing_url(url_to_predict, model_path="./roberta_classifier"):
+    config = PeftConfig.from_pretrained(model_path)
+    inference_model = RobertaForSequenceClassification.from_pretrained(config.base_model_name_or_path, num_labels=2)
+    inference_model = PeftModel.from_pretrained(inference_model, model_path)
+    inference_tokenizer = RobertaTokenizerFast.from_pretrained(model_path)
+
+    inference_model.to("cpu")
+    inference_model.eval()
+
+    inputs = inference_tokenizer(url_to_predict, padding='max_length', truncation=True, max_length=128, return_tensors="pt").to("cpu")
+
+    with torch.no_grad():
+        outputs = inference_model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        predicted_class_id = torch.argmax(predictions).item()
+        probability_phishing = predictions[0, 1].item()
+
+    result = "Phishing" if predicted_class_id == 1 else "Legitimate"
+    return f"{result} (Confidence: {probability_phishing:.2f})"
+
+# Gradio interface
+iface = gr.Interface(
+    fn=predict_phishing_url,
+    inputs=gr.Textbox(lines=1, placeholder="Enter URL..."),
+    outputs="text",
+    title="Phishing URL Detector",
+    description="Enter a URL to classify it as Phishing or Legitimate using RoBERTa-LoRA model."
+)
+
+iface.launch()
+

requirements.txt

@@ -0,0 +1,149 @@
+accelerate==1.7.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.0
+aiosignal==1.3.2
+anyio==4.9.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==3.0.0
+async-lru==2.0.5
+async-timeout==5.0.1
+attrs==25.3.0
+babel==2.17.0
+beautifulsoup4==4.13.4
+bleach==6.2.0
+certifi @ file:///croot/certifi_1745939216646/work/certifi
+cffi==1.17.1
+charset-normalizer @ file:///croot/charset-normalizer_1721748349566/work
+comm==0.2.2
+contourpy==1.3.2
+cycler==0.12.1
+datasets==3.6.0
+debugpy==1.8.14
+decorator==5.2.1
+defusedxml==0.7.1
+dill==0.3.8
+exceptiongroup==1.3.0
+executing==2.2.0
+fastjsonschema==2.21.1
+filelock @ file:///croot/filelock_1744281381737/work
+fonttools==4.58.0
+fqdn==1.5.1
+frozenlist==1.6.0
+fsspec==2025.3.0
+gmpy2 @ file:///croot/gmpy2_1738085463648/work
+h11==0.16.0
+hf-xet==1.1.2
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.32.0
+idna @ file:///croot/idna_1714398848350/work
+ipykernel==6.29.5
+ipython==8.36.0
+ipywidgets==8.1.7
+isoduration==20.11.0
+jedi==0.19.2
+Jinja2 @ file:///croot/jinja2_1741710844255/work
+joblib==1.5.1
+json5==0.12.0
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2025.4.1
+jupyter==1.1.1
+jupyter-console==6.6.3
+jupyter-events==0.12.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.16.0
+jupyter_server_terminals==0.5.3
+jupyterlab==4.4.2
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.15
+kiwisolver==1.4.8
+MarkupSafe @ file:///croot/markupsafe_1738584038848/work
+matplotlib==3.10.3
+matplotlib-inline==0.1.7
+mistune==3.1.3
+mkl-service==2.4.0
+mkl_fft @ file:///io/mkl313/mkl_fft_1730824109137/work
+mkl_random @ file:///io/mkl313/mkl_random_1730823916628/work
+mpmath @ file:///croot/mpmath_1690848262763/work
+multidict==6.4.4
+multiprocess==0.70.16
+nbclient==0.10.2
+nbconvert==7.16.6
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx @ file:///croot/networkx_1737039604450/work
+notebook==7.4.2
+notebook_shim==0.2.4
+numpy @ file:///croot/numpy_and_numpy_base_1725470312869/work/dist/numpy-2.0.1-cp310-cp310-linux_x86_64.whl#sha256=120568f3fd675f59e4cb6de79a5c193b4067d90878d8bab2040fda8e3a2df6fa
+overrides==7.7.0
+packaging==25.0
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+peft==0.15.2
+pexpect==4.9.0
+pillow @ file:///croot/pillow_1744613067434/work
+platformdirs==4.3.8
+prometheus_client==0.22.0
+prompt_toolkit==3.0.51
+propcache==0.3.1
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==20.0.0
+pycparser==2.22
+Pygments==2.19.1
+pyparsing==3.2.3
+PySocks @ file:///home/builder/ci_310/pysocks_1640793678128/work
+python-dateutil==2.9.0.post0
+python-json-logger==3.3.0
+pytz==2025.2
+PyYAML @ file:///croot/pyyaml_1728657952215/work
+pyzmq==26.4.0
+referencing==0.36.2
+regex==2024.11.6
+requests @ file:///croot/requests_1730999120400/work
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.25.1
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+seaborn==0.13.2
+Send2Trash==1.8.3
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.7
+stack-data==0.6.3
+sympy==1.13.1
+terminado==0.18.1
+threadpoolctl==3.6.0
+tinycss2==1.4.0
+tokenizers==0.21.1
+tomli==2.2.1
+torch==2.5.1
+torchaudio==2.5.1
+torchvision==0.20.1
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.52.3
+triton==3.1.0
+types-python-dateutil==2.9.0.20250516
+typing_extensions @ file:///croot/typing_extensions_1734714854207/work
+tzdata==2025.2
+uri-template==1.3.0
+urllib3 @ file:///croot/urllib3_1737133630106/work
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+widgetsnbextension==4.0.14
+xxhash==3.5.0
+yarl==1.20.0

roberta_classifier/README.md

@@ -0,0 +1,202 @@
+---
+base_model: roberta-base
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

roberta_classifier/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

roberta_classifier/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6ce7d7ff34da99997e1a5f2f370f65c696d300baf215d535577b61e9b252ff
+size 3555504

roberta_classifier/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

roberta_classifier/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

roberta_classifier/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f37f0e45713ed68865f1e7a893aceb9712e4544f612ae9dc4673423bd9d048
+size 5176