Train inversion models to synthesize full reasoning traces from reasoning summaries ("bubbles"), then use those synthesized traces to train student models to perform capability stealing attack..
☆24Mar 6, 2026Updated 7 months ago
Alternatives and similar repositories for Trace_Inversion_Attack
Users that are interested in Trace_Inversion_Attack are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Jul 2, 2026Updated 3 months ago
- ☆15Aug 9, 2025Updated last year
- ☆28Dec 15, 2025Updated 10 months ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆37Dec 2, 2025Updated 10 months ago
- [EMNLP 2026] PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization☆20Aug 21, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆13Apr 5, 2026Updated 6 months ago
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆20Dec 31, 2025Updated 9 months ago
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 11 months ago
- An easy to use off-policy synthetic data distillation engine for LLMs.☆20Oct 4, 2026Updated 2 weeks ago
- EMNLP 2025 - "Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs", Official Implementation☆14Oct 18, 2025Updated last year
- Official Codebase of the ACL 2026 Oral paper "Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contra…☆28Jun 25, 2026Updated 3 months ago
- multi-bit language model watermarking (NAACL 24)☆23Sep 20, 2024Updated 2 years ago
- self-hosted github runners☆18Updated this week
- Initial Exploratory Works on Knowledge Tracing in Transformer Based Language Models☆12Feb 21, 2024Updated 2 years ago
- 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.
- The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)☆31Oct 31, 2022Updated 3 years ago
- [ICLR 2026] Data and Code for Paper Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models☆13Feb 2, 2026Updated 8 months ago
- [NDSS 2026] Official repo for Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography☆65Mar 14, 2026Updated 7 months ago
- 1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions☆37Updated this week
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆35Sep 30, 2026Updated 2 weeks ago
- ☆37Oct 5, 2026Updated 2 weeks ago
- ☆12Sep 8, 2023Updated 3 years ago
- Official repo of our paper: Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation☆13Sep 24, 2024Updated 2 years ago
- DICE: Detecting In-distribution Data Contamination with LLM's Internal State☆11Sep 21, 2024Updated 2 years 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.
- ☆22Sep 9, 2024Updated 2 years ago
- An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluat…☆64Oct 8, 2026Updated last week
- ☆48May 29, 2026Updated 4 months ago
- ☆11Sep 16, 2025Updated last year
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆16Feb 1, 2025Updated last year
- Implement of Implicit Knowledge Extraction Attack.☆25Jul 14, 2026Updated 3 months ago
- [EMNLP 2026 Findings] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs☆72Aug 26, 2026Updated last month
- Implementation of the paper "LLMs can hide text in other text of the same length"☆20Oct 24, 2025Updated 11 months ago
- Official implementation of the USENIX Security 2024 paper ModelGuard: Information-Theoretic Defense Against Model Extraction Attacks.☆25Dec 6, 2023Updated 2 years ago
- 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.
- Awesome tools for interpreting, manipulating the internals of of deep neural networks.☆20Oct 13, 2026Updated last week
- A spreadsheet-esque editor to make it easier to select and document electronic parts☆13Jun 7, 2023Updated 3 years ago
- A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation☆17Aug 28, 2025Updated last year
- Claude Code-compatible command hooks for the Pi coding agent☆21May 8, 2026Updated 5 months ago
- The official implementation for "Mitigating Overthinking in Large Reasoning Models via Manifold Steering"☆16May 29, 2025Updated last year
- Code repository for the ICML 2026 Oral paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".☆21Jun 21, 2026Updated 3 months ago
- ☆32Oct 27, 2025Updated 11 months ago