dessertlab / EVIL
EVIL (Exploiting software VIa natural Language) is an approach to automatically generate software exploits in assembly/Python language from descriptions in natural language. The approach leverages Neural Machine Translation (NMT) techniques and a dataset that we developed for this work.
☆28Updated 2 years ago
Alternatives and similar repositories for EVIL:
Users that are interested in EVIL are comparing it to the libraries listed below
- code and data for paper "Automatic Generation and Summarization of Shellcode via Transformer and Dual Learning", which accepted in SANER …☆13Updated 2 years ago
- ☆26Updated last year
- LLAP is an LLVM-based tool for generating enriched program dependency graphs (ePDGs) from program source code that are suitable for use i…☆13Updated last year
- Shellcode_IA32 is a dataset consisting of challenging but common assembly instructions, collected from real shellcodes, with their natura…☆37Updated last year
- AutoVAS is an automated vulnerability analysis system with a deep learning approach.☆35Updated 3 years ago
- A Semantics-Enhanced Learnable Vulnerability Detector☆43Updated 2 years ago
- ACSAC 2018 paper: Towards Automated Generation of Exploitation Primitives for Web Browsers☆14Updated 6 years ago
- The public dataset in the paper "PatchDB: A Large-Scale Security Patch Dataset". This paper appears in the 51st Annual IEEE/IFIP Interna…☆38Updated last year
- Toy implementation of a Automated Exploit Generation built on Angr; stiched using radare, pwntools, pyelftools, and Angrop.☆18Updated 3 years ago
- VulZoo: A Comprehensive Vulnerability Intelligence Dataset (ASE 2024 Demo)☆30Updated 3 months ago
- The source code (including datasets) of V1SCAN (USENIX Security 2023; will be uploaded).☆41Updated last year
- AIBugHunter: A Practical Tool for Predicting, Classifying and Repairing Software Vulnerabilities☆38Updated 10 months ago
- ☆11Updated last year
- ☆10Updated 4 years ago
- Replication Package for "Compressing Pre-trained Models of Code into 3 MB", ASE 2022☆27Updated 4 months ago
- ☆11Updated 3 years ago
- The prototype system of paper Similarity Metric Method for Binary Basic Blocks of Cross-Instruction Set Architecture.☆28Updated 2 years ago
- Fuzz testing framework for binary programs using AI☆49Updated last year
- A Unit-Based Symbolic Execution Method for Detecting Heap Overflow Vulnerability in Executable Codes☆22Updated 2 years ago
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench☆49Updated 2 weeks ago
- ExploitGen is a template-augmented Exploit Code generation method based on CodeBERT, which accepted in JSS.☆9Updated last year
- Tzer: TVM Implementation of "Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation (OOPSLA'22)“.☆13Updated 3 years ago
- SymFusion: Hybrid Instrumentation for Concolic Execution☆16Updated last year
- Practical Data-Only Attack Generation☆34Updated 8 months ago
- A graph-based deep learning tool that can recognizes the kernel objects from raw memory dumps.☆13Updated 5 years ago
- ☆14Updated 2 years ago
- ☆23Updated 2 years ago
- ☠️ Ground-truth dataset for vulnerability prediction (known research datasets and data sources included such as NVD, CVE Details and OSV)…☆86Updated last year
- Python GUI for seeing what's happening inside a fuzzer☆26Updated 3 years ago
- Neural Variable Renaming for Decompiled Binaries☆44Updated 4 years ago