Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses
☆29Feb 11, 2025Updated last year
Alternatives and similar repositories for obfuscated-activations
Users that are interested in obfuscated-activations are comparing it to the libraries listed below
Sorting:
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- ☆14Mar 9, 2025Updated 11 months ago
- ☆20Nov 15, 2024Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆19Feb 16, 2026Updated 2 weeks ago
- Jax Decompiler☆16Apr 22, 2025Updated 10 months ago
- Unofficial faiss wheel builder for NVIDIA GPU☆33Feb 24, 2026Updated last week
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆128Jul 7, 2025Updated 7 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- Is Vec2Text Really a Threat toDense Retrieval Systems?☆19Nov 29, 2024Updated last year
- ☆48Sep 29, 2024Updated last year
- ☆20Feb 11, 2024Updated 2 years ago
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆21Oct 1, 2022Updated 3 years ago
- (ICLR25 Oral) Do as We Do, Not as You Think: the Conformity of Large Language Models☆38Feb 6, 2026Updated 3 weeks ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆31Sep 18, 2025Updated 5 months ago
- Fluent student-teacher redteaming☆23Jul 25, 2024Updated last year
- An open source library for asynchronous querying of LLM endpoints☆36Jul 18, 2025Updated 7 months ago
- ☆41Jul 6, 2025Updated 7 months ago
- Parallel hyperparameter tuning with JAX☆39Jul 21, 2025Updated 7 months ago
- LLMProc: Unix-inspired runtime that treats LLMs as processes.☆34Jul 17, 2025Updated 7 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆81Sep 1, 2025Updated 6 months ago
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆29Nov 19, 2023Updated 2 years ago
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- ☆27Nov 9, 2022Updated 3 years ago
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆88Feb 3, 2026Updated last month
- Inference API for many LLMs and other useful tools for empirical research☆107Updated this week
- ☆11Mar 4, 2020Updated 6 years ago
- ☆13Oct 5, 2025Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆90Dec 31, 2025Updated 2 months ago
- ☆11Dec 23, 2024Updated last year
- ☆35May 21, 2025Updated 9 months ago
- Universal Robustness Evaluation Toolkit (for Evasion)☆32Sep 17, 2025Updated 5 months ago
- Bad Characters: Imperceptible NLP Attacks☆35Apr 9, 2024Updated last year
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 8 months ago
- Measuring the situational awareness of language models☆40Feb 12, 2024Updated 2 years ago
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆31Aug 14, 2025Updated 6 months ago
- ☆12May 6, 2022Updated 3 years ago
- SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation (ICCV 2025)☆14Sep 26, 2025Updated 5 months ago
- Build an AI bot in Discord to serve user's personalized reports on what's up in tech☆28Sep 14, 2025Updated 5 months ago