[NDSS'25] The official implementation of safety misalignment.
☆17Jan 8, 2025Updated last year
Alternatives and similar repositories for misalignment
Users that are interested in misalignment are comparing it to the libraries listed below
Sorting:
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆61Sep 5, 2025Updated 5 months ago
- ☆14Feb 26, 2025Updated last year
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆59Oct 28, 2025Updated 4 months ago
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆14Apr 8, 2025Updated 10 months ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆14Feb 6, 2024Updated 2 years ago
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated 6 months ago
- Red Queen Dataset and data generation template☆26Dec 26, 2025Updated 2 months ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆16Oct 14, 2024Updated last year
- CVPR 2025 - R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning☆21Aug 28, 2025Updated 6 months ago
- ☆24Feb 17, 2026Updated last week
- Code to replicate the Representation Noising paper and tools for evaluating defences against harmful fine-tuning☆23Dec 12, 2024Updated last year
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆19Feb 18, 2025Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆37Feb 3, 2026Updated 3 weeks ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?"☆21Dec 26, 2025Updated 2 months ago
- ☆55Feb 19, 2023Updated 3 years ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆25Sep 10, 2024Updated last year
- ☆24Dec 8, 2024Updated last year
- This is the repository that introduces research topics related to protecting intellectual property (IP) of AI from a data-centric perspec…☆23Oct 30, 2023Updated 2 years ago
- A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions thro…☆63Jan 9, 2026Updated last month
- [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data☆33Apr 7, 2025Updated 10 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆87May 9, 2025Updated 9 months ago
- ☆39May 17, 2025Updated 9 months ago
- ☆11Dec 23, 2024Updated last year
- ☆37Sep 30, 2024Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Dec 16, 2022Updated 3 years ago
- ☆14Aug 7, 2025Updated 6 months ago
- vTPM with SGX protection☆11May 30, 2019Updated 6 years ago
- [Neurips 2025]StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models☆26Dec 4, 2025Updated 2 months ago
- ☆12May 6, 2022Updated 3 years ago
- BrainWash: A Poisoning Attack to Forget in Continual Learning☆12Apr 15, 2024Updated last year
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated last year
- On the Robustness of GUI Grounding Models Against Image Attacks☆12Apr 8, 2025Updated 10 months ago
- The artifact for NDSS '25 paper "ASGARD: Protecting On-Device Deep Neural Networks with Virtualization-Based Trusted Execution Environmen…☆14Oct 16, 2025Updated 4 months ago
- [USENIX'25] HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns☆13Mar 1, 2025Updated 11 months ago
- ☆117Jul 2, 2024Updated last year
- ☆44Oct 1, 2024Updated last year
- ☆48Sep 29, 2024Updated last year
- [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models☆51Jan 11, 2025Updated last year
- ☆125Jul 7, 2025Updated 7 months ago