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…
☆74Updated 2 months 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.☆88Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆348Updated 3 weeks ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆172Updated 7 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆75Updated 3 months ago
- This repository provides a benchmark for prompt injection attacks and defenses☆333Updated 3 weeks ago
- ☆93Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆194Updated 11 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆165Updated 7 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆169Updated 11 months ago
- ☆67Updated 11 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆55Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆361Updated 9 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆61Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆25Updated last month
- ☆49Updated last year
- ☆111Updated 2 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆98Updated last year
- Agent Security Bench (ASB)☆144Updated 3 weeks ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆435Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- Fluent student-teacher redteaming☆23Updated last year
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆155Updated 11 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆300Updated 6 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆52Updated last week
- Official implementation of the WASP web agent security benchmark☆53Updated 3 months ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆55Updated this week
- Jailbreak artifacts for JailbreakBench☆72Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆91Updated last year
- ☆98Updated last year
- ☆24Updated 2 months ago