microsoft / TaskTrackerLinks
TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a simple linear probe-based method and a more sophisticated metric learning method to achieve this. The project also releases the computationally expensive activation data to stimulate further AI safety research…
☆64Updated 2 weeks ago
Alternatives and similar repositories for TaskTracker
Users that are interested in TaskTracker are comparing it to the libraries listed below
Sorting:
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆79Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆70Updated last month
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆169Updated 5 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆270Updated 2 weeks ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆54Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆343Updated 7 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- This repository provides a benchmark for prompt Injection attacks and defenses☆282Updated 2 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆166Updated 9 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆185Updated 9 months ago
- ☆62Updated 8 months ago
- ☆74Updated last year
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆114Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆58Updated 10 months ago
- ☆107Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆232Updated 11 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆147Updated 9 months ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆48Updated 2 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆89Updated 11 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆148Updated 5 months ago
- ☆34Updated 10 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆46Updated last month
- ☆86Updated 9 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆416Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆114Updated last year
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆55Updated 3 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆414Updated 5 months ago
- Fluent student-teacher redteaming☆22Updated last year
- Papers about red teaming LLMs and Multimodal models.☆136Updated 3 months ago