brian-lou / Training-Data-Extraction-Attack-on-LLMsLinks
This project explores training data extraction attacks on the LLaMa 7B, GPT-2XL, and GPT-2-IMDB models to discover memorized content using perplexity, perturbation scoring metrics, and large scale search queries.
☆15Updated 2 years ago
Alternatives and similar repositories for Training-Data-Extraction-Attack-on-LLMs
Users that are interested in Training-Data-Extraction-Attack-on-LLMs are comparing it to the libraries listed below
Sorting:
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆66Updated 3 weeks ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆41Updated 2 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆184Updated 10 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆79Updated 5 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆65Updated last year
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆27Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆57Updated last year
- LLM security and privacy☆53Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆377Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆152Updated 5 months ago
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆103Updated last year
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆13Updated last year
- ☆114Updated 2 months ago
- Implementation for "RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content"☆22Updated last year
- ☆116Updated 9 months ago
- ☆29Updated 8 months ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆18Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆197Updated 10 months ago
- Synthetic Data Generation using LLM via Argilla, Distilabel, ChatGPT, etc.☆30Updated last year
- Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the Over…☆13Updated 2 years ago
- [NeurIPS'24] Protecting Your LLMs with Information Bottleneck☆25Updated last year
- Security Attacks on LLM-based Code Completion Tools (AAAI 2025)☆21Updated last month
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆162Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆391Updated 3 months ago
- ☆56Updated 11 months ago
- Create a knowledge graph out of unstructed legal text - use said knowledge graph in a graph augmented retrieval augmented generation pipe…☆67Updated last year
- An advanced distributed knowledge fabric for intelligent document processing, featuring multi-document agents, optimized query handling, …☆50Updated 3 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆90Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆109Updated last year
- ☆19Updated last year