Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs
☆34Sep 19, 2025Updated last year
Alternatives and similar repositories for Attention-Tracker
Users that are interested in Attention-Tracker are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Implementation of AttnTrace☆16Apr 23, 2026Updated 6 months ago
- [EMNLP 2026] PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization☆20Aug 21, 2026Updated 2 months ago
- ☆15Nov 29, 2025Updated 11 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆80Nov 10, 2025Updated last year
- The implementation for paper "UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in …☆17Jul 3, 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.
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆57Aug 31, 2026Updated 2 months ago
- [EMNLP 2025 - Oral] MovieCORE: COgnitive REasoning in Movies☆12Sep 2, 2025Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆515Sep 27, 2026Updated last month
- Repo for the paper "Defending Against Prompt Injection With a Few DefensiveTokens"☆19Nov 10, 2025Updated last year
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆54Jun 1, 2026Updated 5 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆104Jul 2, 2026Updated 4 months ago
- Evaluating Side-Constraint Loss under Context Compaction Code and experiments for the paper. Do LLM agents still obey your standing inst…☆13Oct 14, 2026Updated last month
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆1,049Jun 2, 2026Updated 5 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆162Apr 15, 2024Updated 2 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [S&P 2026] SoK: Evaluating Jailbreak Guardrails for Large Language Models☆51Dec 17, 2025Updated 11 months ago
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆90Dec 4, 2025Updated 11 months ago
- Official Repo for the paper "SecPO: Principled Adversarial Training for Prompt Injection Security"☆14Nov 5, 2026Updated last week
- [ECCV 2026] The code repo of paper "HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task"☆16Jun 21, 2026Updated 4 months ago
- Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for…☆18Nov 3, 2026Updated 2 weeks 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☆61May 6, 2026Updated 6 months ago
- Code for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'☆12Dec 22, 2025Updated 10 months ago
- code of paper "Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM"☆14Nov 17, 2023Updated 3 years ago
- ☆16Sep 29, 2026Updated last month
- 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.
- A benchmark for evaluating realistic preference-following in personalized user-LLM interactions.☆12Mar 13, 2026Updated 8 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆97Sep 1, 2025Updated last year
- EMNLP 25 Oral - AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender☆20Feb 7, 2026Updated 9 months ago
- 外置准星小工具☆15Jun 3, 2026Updated 5 months ago
- [ACL 2026 Main] Official Repo for Paper "Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Ali…☆17Jul 1, 2026Updated 4 months ago
- A tool that is 100% programmed in bash, designed to simplify the work of operations and maintenance personnel.☆31Jan 18, 2024Updated 2 years ago
- Agent Security Bench (ASB)☆333Sep 30, 2026Updated last month
- The official implementation of the work "Can Indirect Prompt Injection Attacks Be Detected and Removed?"☆11Dec 25, 2025Updated 10 months ago
- ☆20Jun 3, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ACL '26] source code for the paper: "Long-Chain Reasoning Distillation via Adaptive Prefix Alignment"☆16Jan 21, 2026Updated 9 months ago
- [ICLR 2026] Official implementation of "ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents"☆27Mar 23, 2026Updated 7 months ago
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆42Nov 9, 2026Updated last week
- Repo for the paper "Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks".☆75Jun 11, 2026Updated 5 months ago
- [EMNLP 2025] Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills☆11Nov 3, 2025Updated last year
- ☆24Oct 19, 2026Updated 3 weeks ago
- 60 Chinese legal AI skills and 33 expert workflows, with Python tools, evaluations and deployable packages. MIT licensed.☆19Oct 14, 2026Updated last month
Are these results useful?