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…
☆60Updated 4 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.☆72Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆209Updated last week
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆51Updated 11 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆61Updated 2 weeks ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆320Updated 5 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆162Updated 3 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆132Updated 3 months ago
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆39Updated last year
- ☆69Updated last year
- ☆34Updated 8 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆246Updated this week
- ☆45Updated 11 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆157Updated 7 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆176Updated 7 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆51Updated 8 months ago
- Fluent student-teacher redteaming☆22Updated 11 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆109Updated last year
- Red-Teaming Language Models with DSPy☆202Updated 5 months ago
- ☆104Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆84Updated 7 months ago
- Jailbreak artifacts for JailbreakBench☆60Updated 8 months ago
- A prompt injection game to collect data for robust ML research☆62Updated 5 months ago
- ☆73Updated last week
- LLM security and privacy☆48Updated 9 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆84Updated 9 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆88Updated last year
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆113Updated last year
- The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word pred…☆97Updated 11 months ago
- ☆58Updated 7 months ago