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…
☆90Sep 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:
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆98Jun 20, 2026Updated last week
- 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
- ☆18Mar 15, 2024Updated 2 years ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆28Sep 19, 2025Updated 9 months ago
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Jan 7, 2022Updated 4 years 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 9 months ago
- [ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms☆42Jun 4, 2025Updated last year
- 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 8 months ago
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 2 years ago
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆37Jun 24, 2025Updated last year
- ☆145Jul 2, 2024Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆630Jun 2, 2026Updated 3 weeks ago
- Official implementation of the WASP web agent security benchmark☆93Apr 13, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆42May 21, 2025Updated last year
- Progent: Securing AI Agents with Privilege Control☆38May 14, 2026Updated last month
- [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…☆55Apr 19, 2026Updated 2 months ago
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆40Sep 17, 2025Updated 9 months ago
- Universal Robustness Evaluation Toolkit (for Evasion)☆32Sep 17, 2025Updated 9 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.
- ☆32Feb 27, 2025Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆30Jul 11, 2023Updated 2 years ago
- Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion☆11Apr 1, 2024Updated 2 years ago
- ☆21Nov 19, 2021Updated 4 years ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆138Apr 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.☆61Apr 20, 2026Updated 2 months ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆25Mar 16, 2022Updated 4 years ago
- ☆10Updated this week
- ☆16Nov 30, 2022Updated 3 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.
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆77Dec 4, 2025Updated 6 months ago
- [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP☆13Aug 17, 2023Updated 2 years ago
- ☆80Mar 30, 2025Updated last year
- TDSC 2022 | An explainable GNN-based Android malware detection system in paper "MsDroid: Identifying Malicious Snippets for Android Malwa…☆67Feb 21, 2024Updated 2 years ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆22Oct 5, 2025Updated 8 months ago
- Code and full version of the paper "Hijacking Attacks against Neural Network by Analyzing Training Data"☆14Feb 28, 2024Updated 2 years ago
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year