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:
- End-to-end implementation of ML-based Android malware detectors.☆12Oct 13, 2026Updated 3 weeks ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆104Jul 2, 2026Updated 4 months ago
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆74Jun 11, 2026Updated 4 months ago
- Code for the paper "Firewalls to Secure Dynamic LLM Agentic Networks"☆30Jun 6, 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
- 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.
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆33Feb 11, 2025Updated last year
- ☆18Mar 15, 2024Updated 2 years ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated last year
- ☆13Jun 29, 2026Updated 4 months ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆34Sep 19, 2025Updated last year
- ☆35Nov 12, 2024Updated last year
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆994Jun 2, 2026Updated 5 months ago
- ☆13Apr 5, 2026Updated 7 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.
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆63Apr 20, 2026Updated 6 months ago
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆26Sep 16, 2025Updated last year
- ☆29Aug 31, 2025Updated last year
- ☆13Jun 19, 2025Updated last year
- ☆69Mar 18, 2026Updated 7 months ago
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆46Aug 12, 2026Updated 2 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆118Sep 27, 2024Updated 2 years ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆86Mar 25, 2026Updated 7 months ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆511Sep 27, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆10Jan 29, 2026Updated 9 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
- ☆15Nov 29, 2025Updated 11 months ago
- ☆13Mar 22, 2025Updated last year
- ☆186Jul 2, 2024Updated 2 years ago
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆21Feb 18, 2025Updated last year
- Repository for the evaluation of the transferabiilty of adversarial examples.☆22Nov 25, 2025Updated 11 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.
- ☆11Apr 30, 2026Updated 6 months ago
- A benchmark for prompt injection detection systems.☆200Apr 16, 2026Updated 6 months ago
- ☆26May 28, 2025Updated last year
- ASIDE: Architectural Separation of Instructions and Data in Language Models [ICLR 2026]☆18Jun 10, 2026Updated 4 months ago
- ☆18Mar 9, 2025Updated last year
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆78Sep 18, 2025Updated last year
- ☆18Mar 30, 2025Updated last year