wbopan / safety-residual-spaceView external linksLinks
☆21Mar 20, 2025Updated 10 months ago
Alternatives and similar repositories for safety-residual-space
Users that are interested in safety-residual-space are comparing it to the libraries listed below
Sorting:
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆47Oct 13, 2025Updated 4 months ago
- ☆14Jun 6, 2023Updated 2 years ago
- ☆21Dec 14, 2023Updated 2 years ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆18Oct 16, 2024Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated last year
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆20Jan 24, 2024Updated 2 years ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆34Oct 23, 2024Updated last year
- This is the official repository for the ICLR 2025 accepted paper Badrobot: Manipulating Embodied LLMs in the Physical World.☆41Jun 26, 2025Updated 7 months ago
- ☆11Dec 23, 2024Updated 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
- [EMNLP 2025] The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Com…☆39Nov 24, 2025Updated 2 months ago
- ☆12May 6, 2022Updated 3 years ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Jul 19, 2024Updated last year
- ☆44Feb 26, 2025Updated 11 months ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆34Jun 29, 2025Updated 7 months ago
- BrainWash: A Poisoning Attack to Forget in Continual Learning☆12Apr 15, 2024Updated last year
- On the Robustness of GUI Grounding Models Against Image Attacks☆12Apr 8, 2025Updated 10 months ago
- Implementation of LaViC (KDD 2025)☆13Jun 1, 2025Updated 8 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Dec 24, 2023Updated 2 years ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆36Updated this week
- SemEval2026 Task 3 DimABSA☆26Feb 10, 2026Updated last week
- ☆38Oct 2, 2024Updated last year
- [CVPR 2021] Official repository for "Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing"☆39Aug 28, 2022Updated 3 years ago
- ☆15Feb 11, 2025Updated last year
- ☆14Feb 26, 2025Updated 11 months ago
- ☆13Mar 9, 2025Updated 11 months ago
- [ICLR 2022] Boosting Randomized Smoothing with Variance Reduced Classifiers☆12Mar 29, 2022Updated 3 years ago
- ☆20Feb 3, 2025Updated last year
- Code for AISTATS'25 paper - On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond☆13Sep 23, 2025Updated 4 months ago
- Official frontend web application for Moltbook - The Social Network for AI Agents. Built with Next.js 14, TypeScript, Tailwind CSS featur…☆25Feb 1, 2026Updated 2 weeks ago
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆13Dec 16, 2024Updated last year
- ☆11Aug 31, 2025Updated 5 months ago
- ☆14Jun 18, 2024Updated last year
- The implementation of our IEEE S&P 2024 paper "Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples".☆11Jun 28, 2024Updated last year
- (WWW'25 + Netflix) The first CRS that retrieves collaborative filtering knowledge with two-step context-aware reflection.☆18Sep 10, 2025Updated 5 months ago
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆38Updated this week
- ☆21Jun 22, 2025Updated 7 months ago
- ☆12Nov 1, 2024Updated last year