This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"
☆49Oct 13, 2025Updated 8 months ago
Alternatives and similar repositories for AI-Safety_SCAV
Users that are interested in AI-Safety_SCAV are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆22Mar 20, 2025Updated last year
- ☆39Oct 15, 2024Updated last year
- ☆17May 17, 2025Updated last year
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆50Jan 15, 2026Updated 4 months ago
- The official repository for guided jailbreak benchmark☆29Jul 28, 2025Updated 10 months 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.
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆12Oct 31, 2024Updated last year
- ☆14Jun 6, 2023Updated 3 years ago
- [Preprint] Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis☆10Sep 23, 2021Updated 4 years ago
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆32Jul 31, 2025Updated 10 months ago
- Official repository for "Boosting Adversarial Transferability using Dynamic Cues " (ICLR 2023)☆20Aug 24, 2023Updated 2 years ago
- The implement of paper:"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability"☆67Jun 3, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆263Sep 24, 2024Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆90Mar 30, 2025Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆15Jan 13, 2023Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆39Jun 28, 2025Updated 11 months ago
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆34Jul 20, 2025Updated 10 months ago
- Repo for paper "Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability"☆108Apr 23, 2026Updated last month
- Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning [Accepted at ICML 2023]☆14Mar 31, 2024Updated 2 years ago
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆18Mar 12, 2025Updated last year
- ☆45Oct 1, 2024Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆336May 13, 2025Updated last year
- The official implementation of Preference Data Reward-Augmentation.☆18May 1, 2025Updated last year
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆30Jul 29, 2024Updated last year
- 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.
- ☆20Jan 13, 2024Updated 2 years ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆183Apr 23, 2025Updated last year
- ☆45Jun 19, 2025Updated 11 months ago
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆29Dec 21, 2025Updated 5 months ago
- ICL backdoor attack☆17Nov 4, 2024Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆121Mar 26, 2024Updated 2 years ago
- ☆53Feb 8, 2025Updated last year
- ☆22Oct 25, 2024Updated last year
- Algebraic value editing in pretrained language models☆70Nov 1, 2023Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)☆22Oct 16, 2025Updated 7 months ago
- Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.☆18May 31, 2023Updated 3 years ago
- Repository for the Paper: Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Inj…☆19Apr 17, 2026Updated last month
- ☆22Dec 14, 2023Updated 2 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- Self-Teaching Notes on Gradient Leakage Attacks against GPT-2 models.☆14Mar 18, 2024Updated 2 years ago
- FGLA: Fast Generation-Based Gradient Leakage Attacks against Highly Compressed Gradients☆14Mar 17, 2026Updated 2 months ago