microsoft / TaskTrackerLinks
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…
☆56Updated 3 months ago
Alternatives and similar repositories for TaskTracker
Users that are interested in TaskTracker are comparing it to the libraries listed below
Sorting:
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆70Updated last year
- ☆116Updated 2 weeks ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆51Updated 2 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆69Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆193Updated last week
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆51Updated 10 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- ☆66Updated 11 months ago
- ☆46Updated 10 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆174Updated 6 months ago
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆54Updated 3 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆50Updated 8 months ago
- Fluent student-teacher redteaming☆22Updated 11 months ago
- ☆35Updated 7 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆64Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆82Updated 6 months ago
- Jailbreak artifacts for JailbreakBench☆60Updated 7 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 7 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆39Updated 3 weeks ago
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆34Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆159Updated 2 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆108Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆215Updated 9 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆133Updated 11 months ago
- ☆58Updated 6 months ago
- A prompt injection game to collect data for robust ML research☆62Updated 5 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆80Updated 9 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆319Updated 5 months ago
- [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`☆74Updated 3 months ago
- Dataset for the Tensor Trust project☆43Updated last year