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…
☆87Sep 1, 2025Updated 7 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☆22Apr 9, 2026Updated 3 weeks ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆96Apr 14, 2026Updated 2 weeks ago
- CCS 2023 | Explainable malware and vulnerability detection with XAI in paper "FINER: Enhancing State-of-the-art Classifiers with Feature …☆11Aug 20, 2024Updated last year
- ☆18Mar 15, 2024Updated 2 years ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆23Sep 19, 2025Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆29Aug 31, 2025Updated 8 months ago
- [ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms☆40Jun 4, 2025Updated 10 months ago
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆31Feb 11, 2025Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated 6 months ago
- Code for the paper "Firewalls to Secure Dynamic LLM Agentic Networks"☆30Jun 6, 2025Updated 10 months ago
- ☆25May 28, 2025Updated 11 months ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Oct 3, 2023Updated 2 years ago
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆33Jun 24, 2025Updated 10 months ago
- ☆132Jul 2, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆14Jun 6, 2023Updated 2 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆546Mar 30, 2026Updated last month
- Official implementation of the WASP web agent security benchmark☆83Apr 13, 2026Updated 2 weeks ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆112Sep 27, 2024Updated last year
- ☆39May 21, 2025Updated 11 months ago
- ☆33Sep 11, 2025Updated 7 months ago
- [Findings of ACL 2023] Bridge the Gap Between CV and NLP! A Optimization-based Textual Adversarial Attack Framework.☆14Aug 27, 2023Updated 2 years ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆47Apr 19, 2026Updated last week
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆60Apr 29, 2022Updated 4 years ago
- 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.
- Official Repository of the Entity-based Reinforcement Learning for Autonomous Cyber Defence paper.☆18Jan 24, 2025Updated last year
- ☆15Jun 7, 2024Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- This repository contains code and data of the paper **On the Limitations of Continual Learning for Malware Classification**, accepted to …☆19Dec 29, 2023Updated 2 years ago
- PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents (TDSC 2024)☆20Mar 29, 2024Updated 2 years ago
- Erlang/OTP MTA (Mail Transfer Agent)☆29Jul 8, 2014Updated 11 years ago
- ☆31Feb 27, 2025Updated last year
- ☆29Sep 15, 2024Updated last year
- Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion☆11Apr 1, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆10Sep 24, 2021Updated 4 years ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆119Apr 15, 2024Updated 2 years ago
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆60Apr 20, 2026Updated last week
- TI-RSLK_小车走迷宫☆14Apr 27, 2019Updated 7 years ago
- ☆10Mar 10, 2026Updated last month
- ☆16Nov 30, 2022Updated 3 years ago
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆76Dec 4, 2025Updated 4 months ago