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.
☆68Dec 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:
- This research proposes defense strategies against prompt injection in large language models to improve their robustness and security agai…☆13Jun 24, 2023Updated 3 years ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆511Sep 27, 2026Updated last month
- Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the Over…☆13Aug 21, 2023Updated 3 years ago
- The Security Toolkit for managing Generative AI(especially LLMs) and Supervised Learning processes(Learning and Inference).☆23Jun 25, 2025Updated last year
- Curated UTF-8 URL-encoded character dictionary for injection testing, fuzzing, and bypass techniques against web applications and APIs, f…☆13Sep 20, 2021Updated 5 years 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.
- Machine Learning-based tool for Cybersecurity Risk Assessment☆14Jul 18, 2021Updated 5 years ago
- A frontend for privateGPT☆11Jan 20, 2024Updated 2 years ago
- This Repo focuses on defending against 'adversarial prompts,' detecting and attempting to mitigate objectionable content in real time.☆14Jul 30, 2023Updated 3 years ago
- Building your GPT-based private knowledge hub using zkSNARK & PLONK☆13Jun 20, 2023Updated 3 years ago
- Exploit for CVE-2024-3273, supports single and multiple hosts☆13Apr 7, 2024Updated 2 years ago
- 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
- ☆18May 22, 2024Updated 2 years ago
- Machine Learning Security Principles, published by Packt☆24Apr 22, 2026Updated 6 months ago
- Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge☆28Nov 1, 2026Updated last week
- 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.
- The automated prompt injection framework for LLM-integrated applications.☆280Sep 12, 2024Updated 2 years ago
- 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
- This GenAI demo project, built with CrewAI and AutoGen, showcases potential security risks associated with AI agents.☆17May 1, 2025Updated last year
- ☆16Aug 8, 2023Updated 3 years ago
- ☆14Oct 9, 2020Updated 6 years ago
- Enter a link, downloads the file on the server☆10Nov 23, 2018Updated 7 years ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆45Apr 20, 2026Updated 6 months ago
- A repository of awesome open source projects to set up your own AI powered knowledge base☆10Jul 19, 2023Updated 3 years ago
- ☆27May 2, 2026Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A portfolio demonstrating advanced blue and red team skills, including: SSH MFA implementation, Volatility-based memory forensics to dete…☆24Oct 19, 2025Updated last year
- GitHub Advisory Database RSS Feeds.☆14Updated this week
- LLM Prompt Injection Detector☆1,532Aug 7, 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
- Risks and targets for assessing LLMs & LLM vulnerabilities☆36May 27, 2024Updated 2 years ago
- Use machine learning to classify malware. Malware analysis 101. Set up a cybersecurity lab environment. Learn how to tackle data class im…☆18Jul 11, 2026Updated 3 months ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆120Oct 11, 2024Updated 2 years ago
- ☆15May 10, 2023Updated 3 years ago
- A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.☆22Apr 8, 2026Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Application scanning component of OWASP PurpleTeam☆16Feb 12, 2023Updated 3 years ago
- New ways of breaking app-integrated LLMs☆2,152Jul 17, 2025Updated last year
- ☆10Jan 29, 2026Updated 9 months ago
- AIxCC: automated vulnerability repair via LLMs, search, and static analysis☆13Jul 16, 2024Updated 2 years ago
- VulnReach builds on standard SCA output by adding reachability context - proving through static analysis, taint tracking, and live runtim…☆23Oct 3, 2026Updated last month
- ☆20Jan 9, 2024Updated 2 years ago
- Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.☆25Oct 6, 2026Updated last month