Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+license: unknown
+library_name: transformers.js
+base_model:
+- phishbot/ScamLLM
+pipeline_tag: text-classification
+---
+
+
+
+# ScamLLM (ONNX)
+
+
+This is an ONNX version of [phishbot/ScamLLM](https://huggingface.co/phishbot/ScamLLM). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
+
+
+## Usage with Transformers.js
+
+
+See the pipeline documentation for `text-classification`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextClassificationPipeline
+
+
+---
+
+
+# Overview
+
+<!-- This model is obtained by finetuning Pre-Trained RoBERTa on dataset containing several sets of malicious prompts.
+Using this model, we can classify malicious prompts that can lead towards creation of phishing websites and phishing emails. 
+This model is obtained by finetuning a Pre-Trained RoBERTa using a dataset encompassing multiple sets of malicious prompts, as detailed in the corresponding arXiv paper. 
+Using this model, we can classify malicious prompts that can lead towards creation of phishing websites and phishing emails. -->
+
+Our model, "ScamLLM" is designed to identify malicious prompts that can be used to generate phishing websites using popular commercial LLMs like ChatGPT, Bard and Claude.
+This model is obtained by finetuning a Pre-Trained RoBERTa using a dataset encompassing multiple sets of malicious prompts. 
+
+Try out "ScamLLM" using the Inference API. Our model classifies prompts with "Label 1" to signify the identification of a phishing attempt, while "Label 0" denotes a prompt that is considered safe and non-malicious.
+
+## Dataset Details
+
+The dataset utilized for training this model has been created using malicious prompts generated using GPT 3.5T and GPT-4. 
+Due to being active vulnerabilities under review, our dataset of malicious prompts is available only upon request at this stage.
+
+## Training Details
+
+The model was trained using RobertaForSequenceClassification.from_pretrained. 
+In this process, both the model and tokenizer pertinent to the RoBERTa-base were employed and trained for 10 epochs (learning rate 2e-5 and AdamW Optimizer). 
+
+## Inference
+
+There are multiple ways to test this model, with the simplest being to use the Inference API, as well as with the pipeline "text-classification" as below:
+
+```python
+from transformers import pipeline
+classifier = pipeline(task="text-classification", model="phishbot/ScamLLM", top_k=None)
+prompt = ["Your Sample Sentence or Prompt...."]
+model_outputs = classifier(prompt)
+print(model_outputs[0])
+```
+
+If you use our model in your research, please cite our paper **"From Chatbots to Phishbots?: Phishing Scam Generation in Commercial Large Language Models"** (https://www.computer.org/csdl/proceedings-article/sp/2024/313000a221/1WPcYLpYFHy). 
+
+BibTeX below:
+
+```@inproceedings{roy2024chatbots,
+  title={From Chatbots to Phishbots?: Phishing Scam Generation in Commercial Large Language Models},
+  author={Roy, Sayak Saha and Thota, Poojitha and Naragam, Krishna Vamsi and Nilizadeh, Shirin},
+  booktitle={2024 IEEE Symposium on Security and Privacy (SP)},
+  pages={221--221},
+  year={2024},
+  organization={IEEE Computer Society}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "phishbot/ScamLLM",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20facf507a3379c1bfffcb69fbc9924c325c2ee788e18179714ddc3fb2378d04
+size 498912894

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1883d40d92b511a119f5fadca7bc88afb6bcdf0eb199e9788687be6f33dde0ee
+size 206961216

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a16682e8df3ff20204178e87e51e66203bf126c9c42e19db582cd481a5d26e
+size 249618877

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579e8db7ff30ac6a3aa7d4144c7cb97bdd8f2ab04ee76293c6893c8eb5d282b9
+size 125855419

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb01a98d28106b15a2f7f62d2556343795bbcdb1d320ef1ea832b24fdc03bdd4
+size 212269104

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b93133302129dae2d6f490689b87e5294b73cb45b59a0c166e4ad492ce9ff0
+size 127536080

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579e8db7ff30ac6a3aa7d4144c7cb97bdd8f2ab04ee76293c6893c8eb5d282b9
+size 125855419

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4fca6a6b1b01bcc0de3e1ccb8499fd9ecd319b85ff7fbd945704d250966f0f
+size 125855419

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}