This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"
☆49Oct 13, 2025Updated 9 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☆23Jun 12, 2026Updated last month
- ☆40Oct 15, 2024Updated last year
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆51Jan 15, 2026Updated 6 months ago
- ☆70Jun 1, 2025Updated last year
- ☆15Jun 6, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- ☆18May 17, 2025Updated last year
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆35Jul 31, 2025Updated 11 months ago
- [Preprint] Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis☆10Sep 23, 2021Updated 4 years ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated last year
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆29Dec 21, 2025Updated 7 months ago
- The official repository for guided jailbreak benchmark☆31Jul 28, 2025Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆266Sep 24, 2024Updated last year
- [ICML 2023] Protecting Language Generation Models via Invisible Watermarking☆13Sep 8, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning [Accepted at ICML 2023]☆14Mar 31, 2024Updated 2 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆15Jan 13, 2023Updated 3 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆15Jul 22, 2025Updated last year
- [EMNLP 2025] Official code for the paper "SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning"☆16May 12, 2026Updated 2 months ago
- Official repository for "Boosting Adversarial Transferability using Dynamic Cues " (ICLR 2023)☆20Aug 24, 2023Updated 2 years ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆344May 13, 2025Updated last year
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆18Mar 12, 2025Updated last year
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"☆26Aug 20, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆31Sep 15, 2024Updated last year
- ☆47Oct 1, 2024Updated last year
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆90Jun 2, 2026Updated last month
- Reproduction Code for Paper "Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models"☆14Jun 1, 2024Updated 2 years ago
- [NeurIPS 2025] Official Implementation for Learning to Steer: Input-dependent Steering for Multimodal LLMs☆19Dec 14, 2025Updated 7 months ago
- The official implementation of Preference Data Reward-Augmentation.☆18May 1, 2025Updated last year
- ☆20Jan 13, 2024Updated 2 years ago
- ☆53Feb 8, 2025Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆123Mar 26, 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.
- [NDSS'25] The official implementation of safety misalignment.☆19Jan 8, 2025Updated last year
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆34Jul 20, 2025Updated last year
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆30Apr 2, 2025Updated last year
- Algebraic value editing in pretrained language models☆71Nov 1, 2023Updated 2 years ago
- Self-Teaching Notes on Gradient Leakage Attacks against GPT-2 models.☆14Mar 18, 2024Updated 2 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 3 months ago
- ☆22Dec 14, 2023Updated 2 years ago