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…
☆89Sep 1, 2025Updated 9 months ago
Alternatives and similar repositories for TaskTracker
Users that are interested in TaskTracker are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge☆25Apr 9, 2026Updated 2 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆96May 6, 2026Updated last month
- ☆18Mar 15, 2024Updated 2 years ago
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years ago
- ☆29Aug 31, 2025Updated 9 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated 8 months ago
- General research for Dreadnode☆27Jun 17, 2024Updated last year
- ☆25May 28, 2025Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Oct 3, 2023Updated 2 years ago
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆36Jun 24, 2025Updated 11 months ago
- ☆14Jun 6, 2023Updated 3 years ago
- Official implementation of the WASP web agent security benchmark☆88Apr 13, 2026Updated last month
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆112Sep 27, 2024Updated last year
- ☆41May 21, 2025Updated last year
- 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.
- Progent: Securing AI Agents with Privilege Control☆36May 14, 2026Updated 3 weeks ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆51Apr 19, 2026Updated last month
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆40Sep 17, 2025Updated 8 months ago
- ☆15Jun 7, 2024Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- Universal Robustness Evaluation Toolkit (for Evasion)☆32Sep 17, 2025Updated 8 months ago
- ☆60Mar 9, 2023Updated 3 years ago
- This repository contains code and data of the paper **On the Limitations of Continual Learning for Malware Classification**, accepted to …☆20Dec 29, 2023Updated 2 years ago
- PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents (TDSC 2024)☆19Mar 29, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Erlang/OTP MTA (Mail Transfer Agent)☆29Jul 8, 2014Updated 11 years ago
- ☆31Feb 27, 2025Updated last year
- Docker container escape enumeration tool.☆12Jan 23, 2021Updated 5 years ago
- ☆31Sep 15, 2024Updated last year
- Practical Jupyter notebooks from Andrew Ng and Giskard team's "Red Teaming LLM Applications" course on DeepLearning.AI.☆23Apr 8, 2024Updated 2 years ago
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆30Jul 11, 2023Updated 2 years ago
- Example agents for the Dreadnode platform☆32Dec 19, 2025Updated 5 months ago
- ☆21Nov 19, 2021Updated 4 years ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆131Apr 15, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆61Apr 20, 2026Updated last month
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆25Mar 16, 2022Updated 4 years ago
- 🎮 A configurable Breakout environment for reinforcement learning☆11Mar 20, 2018Updated 8 years ago
- ☆16Nov 30, 2022Updated 3 years ago
- Exploiting Jackson deserialization vulnerability with 3 gadgets☆10May 3, 2021Updated 5 years ago
- [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP☆13Aug 17, 2023Updated 2 years ago
- Data Poisoning in Deep Learning: A Survey☆23May 26, 2026Updated last week