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…
☆93Sep 1, 2025Updated 11 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:
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆99Jul 2, 2026Updated last month
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆70Jun 11, 2026Updated 2 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆77Nov 10, 2025Updated 9 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆152Apr 15, 2024Updated 2 years ago
- CCS 2023 | Explainable malware and vulnerability detection with XAI in paper "FINER: Enhancing State-of-the-art Classifiers with Feature …☆12Aug 20, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Code to generate NeuralExecs (prompt injection for LLMs)☆27Oct 5, 2025Updated 10 months ago
- ☆18Mar 15, 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.☆734Jun 2, 2026Updated 2 months ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆28Sep 19, 2025Updated 10 months ago
- ☆35Nov 12, 2024Updated last year
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years ago
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆22Sep 16, 2025Updated 10 months ago
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆53May 6, 2026Updated 3 months 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☆32Feb 11, 2025Updated last year
- General research for Dreadnode☆28Jun 17, 2024Updated 2 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆116Sep 27, 2024Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 2 years ago
- ☆157Jul 2, 2024Updated 2 years ago
- PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents☆31Mar 26, 2025Updated last year
- ☆15Nov 29, 2025Updated 8 months ago
- 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 3 months ago
- The open-source AISI toolkit for sandboxing agentic evaluations☆27Aug 7, 2025Updated last year
- 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.
- ☆10Dec 14, 2023Updated 2 years ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆474Oct 29, 2025Updated 9 months ago
- ☆18Mar 30, 2025Updated last year
- ASIDE: Architectural Separation of Instructions and Data in Language Models [ICLR 2026]☆17Jun 10, 2026Updated 2 months ago
- Repository for the evaluation of the transferabiilty of adversarial examples.☆21Nov 25, 2025Updated 8 months ago
- ☆17Mar 9, 2025Updated last year
- ☆24Mar 18, 2025Updated last year
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆37Jul 31, 2025Updated last year
- ☆26May 28, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- 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☆61Apr 29, 2022Updated 4 years 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
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆74Mar 25, 2026Updated 4 months ago
- Official Repository of the Entity-based Reinforcement Learning for Autonomous Cyber Defence paper.☆18Jan 24, 2025Updated last year
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆81Dec 4, 2025Updated 8 months ago
- ☆22Jun 12, 2026Updated last month