This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.
☆65Dec 18, 2023Updated 2 years ago
Alternatives and similar repositories for llm-security-prompt-injection
Users that are interested in llm-security-prompt-injection are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context☆19Feb 20, 2026Updated 5 months ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆479Oct 29, 2025Updated 9 months ago
- The following is a simple example of how LLMs and langchain agents can simplify asking questions to understand the security posture of a …☆23Aug 23, 2023Updated 2 years ago
- Curated UTF-8 URL-encoded character dictionary for injection testing, fuzzing, and bypass techniques against web applications and APIs, f…☆14Sep 20, 2021Updated 4 years ago
- A self-assessment tool by @NC3-LU to help business owners implement a better cybersecurity strategy.☆25Feb 13, 2026Updated 6 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- AyedFuzzer is a small File-Format-Fuzzer with 3 options (File-mutating, WinDbg-interactive monitor, multi-processing) for windows executa…☆17Dec 2, 2024Updated last year
- SNMP Bash Script to discover valid community strings, dump basic information, check for write permission and check for RCE.☆11Apr 27, 2024Updated 2 years ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆115Oct 11, 2024Updated last year
- Official repository of the paper: Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code (Findings of EACL …☆13Mar 26, 2026Updated 4 months ago
- Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge☆26Apr 9, 2026Updated 4 months ago
- Master PDF Summarization with Google Bard☆13Feb 29, 2024Updated 2 years ago
- ☆20Jun 4, 2023Updated 3 years ago
- Code and data for AAAI 2022 paper "Multilingual Code Snippets Training for Program Translation"☆11Mar 7, 2022Updated 4 years ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆46Apr 20, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆171Oct 13, 2023Updated 2 years ago
- Application scanning component of OWASP PurpleTeam☆16Feb 12, 2023Updated 3 years ago
- 1990–2021년 한국어 신문 사회면 기사의 ○○女·○○男 집계☆17Sep 26, 2023Updated 2 years ago
- Guess a person's gender by their first name. Caveats apply.☆18May 6, 2023Updated 3 years ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆36May 27, 2024Updated 2 years ago
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆496Jan 31, 2024Updated 2 years ago
- Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".☆10Feb 6, 2024Updated 2 years ago
- WiP - cve-search next gen☆13Jan 18, 2020Updated 6 years ago
- Simulate Windows EXE for Malware Research!☆21Sep 4, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- "Why do I feel offended?" - Korean Dataset for Offensive Language Identification (EACL2023 Findings)☆15May 14, 2023Updated 3 years ago
- Secure Inference Resilient Against Malicious Clients☆14May 3, 2022Updated 4 years ago
- LLM Program Watermarking☆19Apr 19, 2024Updated 2 years ago
- Leverage the Intel® Distribution of OpenVINO™ Toolkit to fast-track development of high-performance computer vision and deep learning inf…☆10Jul 28, 2020Updated 6 years ago
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Jan 26, 2024Updated 2 years ago
- ☆10Mar 8, 2025Updated last year
- This script searches NVD's website for new CVES, alerting you by email or telegram. You can configure a list of products that interest yo…☆10Mar 21, 2021Updated 5 years ago
- ☆47Jun 29, 2023Updated 3 years ago
- ☆27May 2, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆68Jan 15, 2026Updated 7 months ago
- Social Network Analysis - Zurich Summer School for Women in Political Methodology☆13Sep 6, 2018Updated 7 years ago
- ☆20Jan 9, 2024Updated 2 years ago
- AIxCC: automated vulnerability repair via LLMs, search, and static analysis☆13Jul 16, 2024Updated 2 years ago
- ☆14Jul 12, 2025Updated last year
- Cybersecurity demo for Neo4j's Connections: Graphs in Cybersecurity 2021☆14May 17, 2022Updated 4 years ago
- Machine Learning-based tool for Cybersecurity Risk Assessment☆14Jul 18, 2021Updated 5 years ago