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…
☆97Sep 1, 2025Updated last year
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☆27Updated this week
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆102Jul 2, 2026Updated 3 months ago
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆71Jun 11, 2026Updated 4 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆79Nov 10, 2025Updated 11 months ago
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆33Feb 11, 2025Updated last year
- 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.
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆160Apr 15, 2024Updated 2 years ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated last year
- CCS 2023 | Explainable malware and vulnerability detection with XAI in paper "FINER: Enhancing State-of-the-art Classifiers with Feature …☆12Aug 20, 2024Updated 2 years ago
- Code for the paper "Firewalls to Secure Dynamic LLM Agentic Networks"☆30Jun 6, 2025Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆928Jun 2, 2026Updated 4 months ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆33Sep 19, 2025Updated last year
- ☆35Nov 12, 2024Updated last year
- ☆29Aug 31, 2025Updated last year
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years 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.
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆25Sep 16, 2025Updated last year
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆57May 6, 2026Updated 5 months ago
- General research for Dreadnode☆28Jun 17, 2024Updated 2 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 3 years ago
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆32Mar 26, 2025Updated last year
- ☆15Jun 6, 2023Updated 3 years ago
- ☆17Mar 30, 2025Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆506Sep 27, 2026Updated 3 weeks ago
- Repository for the evaluation of the transferabiilty of adversarial examples.☆22Nov 25, 2025Updated 10 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.
- ☆18Mar 9, 2025Updated last year
- ASIDE: Architectural Separation of Instructions and Data in Language Models [ICLR 2026]☆18Jun 10, 2026Updated 4 months ago
- Implementation of average- and worst-case robust flatness measures for adversarial training.☆15Nov 5, 2021Updated 4 years ago
- The deterministic tax engine for AI agents. Highest score ever recorded on TaxCalcBench (96% exact returns)☆161Updated this week
- The open-source AISI toolkit for sandboxing agentic evaluations☆36Aug 7, 2025Updated last year
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆62Jul 16, 2026Updated 3 months ago
- A benchmark for prompt injection detection systems.☆200Apr 16, 2026Updated 6 months ago
- AI/ML and Cybersecurity: The Emperor has no Clothes☆18Oct 18, 2023Updated 2 years ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆60Apr 29, 2022Updated 4 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.
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆41Sep 17, 2025Updated last year
- ☆24Mar 18, 2025Updated last year
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆88Dec 4, 2025Updated 10 months ago
- ☆15Jun 7, 2024Updated 2 years ago
- Repository for sample Windows applications and tools that use eye tracking☆23Aug 18, 2022Updated 4 years ago
- Code for the paper "Defeating Prompt Injections by Design"☆407Jun 20, 2025Updated last year
- Universal Robustness Evaluation Toolkit (for Evasion)☆32Sep 17, 2025Updated last year