├── README.md ├── cebin-tokenizer ├── added_tokens.json ├── merges.txt ├── special_tokens_map.json ├── tokenizer.json ├── tokenizer_config.json └── vocab.json ├── finetune ├── .gitignore ├── config.py ├── dataset.py ├── demo_comparison.py ├── demo_embedding.py ├── finetune.py ├── finetune_pair.py ├── helper.py ├── models.py ├── preprocess_binarycorp.py ├── preprocess_cisco.py ├── preprocess_trex.py ├── run.sh ├── run_pair.sh └── tokenizer.py ├── pretrain ├── .gitignore ├── dataset.py ├── helper.py ├── models.py ├── pretrain.py ├── run.sh ├── tokenizer.py └── utils │ └── dataset-prepare.py └── vulsearch ├── ann-builder.py ├── collect.py ├── eval.py ├── eval_all.py ├── models.py ├── tokenizer.py └── utils ├── cve-gencsv.py ├── cve-process.py └── dataset-prepare.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/README.md -------------------------------------------------------------------------------- /cebin-tokenizer/added_tokens.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/added_tokens.json -------------------------------------------------------------------------------- /cebin-tokenizer/merges.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/merges.txt -------------------------------------------------------------------------------- /cebin-tokenizer/special_tokens_map.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/special_tokens_map.json -------------------------------------------------------------------------------- /cebin-tokenizer/tokenizer.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/tokenizer.json -------------------------------------------------------------------------------- /cebin-tokenizer/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/tokenizer_config.json -------------------------------------------------------------------------------- /cebin-tokenizer/vocab.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/cebin-tokenizer/vocab.json -------------------------------------------------------------------------------- /finetune/.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | wandb/ 3 | *.yaml -------------------------------------------------------------------------------- /finetune/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/config.py -------------------------------------------------------------------------------- /finetune/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/dataset.py -------------------------------------------------------------------------------- /finetune/demo_comparison.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/demo_comparison.py -------------------------------------------------------------------------------- /finetune/demo_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/demo_embedding.py -------------------------------------------------------------------------------- /finetune/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/finetune.py -------------------------------------------------------------------------------- /finetune/finetune_pair.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/finetune_pair.py -------------------------------------------------------------------------------- /finetune/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/helper.py -------------------------------------------------------------------------------- /finetune/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/models.py -------------------------------------------------------------------------------- /finetune/preprocess_binarycorp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/preprocess_binarycorp.py -------------------------------------------------------------------------------- /finetune/preprocess_cisco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/preprocess_cisco.py -------------------------------------------------------------------------------- /finetune/preprocess_trex.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/preprocess_trex.py -------------------------------------------------------------------------------- /finetune/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/run.sh -------------------------------------------------------------------------------- /finetune/run_pair.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/run_pair.sh -------------------------------------------------------------------------------- /finetune/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/finetune/tokenizer.py -------------------------------------------------------------------------------- /pretrain/.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | wandb/ 3 | config/ 4 | logs/ 5 | models/ 6 | *.csv 7 | results/ -------------------------------------------------------------------------------- /pretrain/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/dataset.py -------------------------------------------------------------------------------- /pretrain/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/helper.py -------------------------------------------------------------------------------- /pretrain/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/models.py -------------------------------------------------------------------------------- /pretrain/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/pretrain.py -------------------------------------------------------------------------------- /pretrain/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/run.sh -------------------------------------------------------------------------------- /pretrain/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/tokenizer.py -------------------------------------------------------------------------------- /pretrain/utils/dataset-prepare.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/pretrain/utils/dataset-prepare.py -------------------------------------------------------------------------------- /vulsearch/ann-builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/ann-builder.py -------------------------------------------------------------------------------- /vulsearch/collect.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/collect.py -------------------------------------------------------------------------------- /vulsearch/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/eval.py -------------------------------------------------------------------------------- /vulsearch/eval_all.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/eval_all.py -------------------------------------------------------------------------------- /vulsearch/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/models.py -------------------------------------------------------------------------------- /vulsearch/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/tokenizer.py -------------------------------------------------------------------------------- /vulsearch/utils/cve-gencsv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/utils/cve-gencsv.py -------------------------------------------------------------------------------- /vulsearch/utils/cve-process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/utils/cve-process.py -------------------------------------------------------------------------------- /vulsearch/utils/dataset-prepare.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Hustcw/CEBin/HEAD/vulsearch/utils/dataset-prepare.py --------------------------------------------------------------------------------