Alibaba-AAIG / OysterView external linksLinks
The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster 系列是 Alibaba-AAIG 自研的安全模型，致力于构建负责任的 AI 生态。
☆59Sep 11, 2025Updated 5 months ago
Alternatives and similar repositories for Oyster
Users that are interested in Oyster are comparing it to the libraries listed below
Sorting:
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆57Jan 23, 2026Updated 3 weeks ago
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Mar 29, 2024Updated last year
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆14Apr 8, 2025Updated 10 months ago
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆16Mar 31, 2025Updated 10 months ago
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆46Nov 5, 2025Updated 3 months ago
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆15Jul 18, 2024Updated last year
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆15Aug 7, 2025Updated 6 months ago
- Official Code and data for ACL 2024 finding, "An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models"☆25Nov 10, 2024Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆23Jul 26, 2024Updated last year
- ☆24Dec 8, 2024Updated last year
- [ICCVW 2025 (Oral)] Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models☆28Oct 20, 2025Updated 3 months ago
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆35Jul 10, 2025Updated 7 months ago
- Emoji Attack [ICML 2025]☆41Jul 15, 2025Updated 7 months ago
- Prompt Generator model for Stable Diffusion Models☆11Jun 20, 2023Updated 2 years ago
- ☆30May 22, 2024Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated 7 months ago
- ☆18Jan 5, 2026Updated last month
- ☆11Jul 31, 2022Updated 3 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
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆24Oct 23, 2025Updated 3 months ago
- ☆57Jun 5, 2024Updated last year
- ☆16Feb 8, 2024Updated 2 years ago
- Accept by CVPR 2025 (highlight)☆22Jun 8, 2025Updated 8 months ago
- The code of "Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds" CVPR 2024☆36Mar 23, 2024Updated last year
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆88Feb 26, 2025Updated 11 months ago
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆31Jun 24, 2025Updated 7 months ago
- ☆17Mar 6, 2023Updated 2 years ago
- ☆121Feb 3, 2025Updated last year
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆87Feb 3, 2026Updated last week
- ☆48Apr 7, 2025Updated 10 months ago
- ☆19Jun 21, 2025Updated 7 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆50Dec 23, 2024Updated last year
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆48Apr 27, 2022Updated 3 years ago
- The code for ECCV2022 (Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal)☆44Oct 1, 2022Updated 3 years ago
- The official repository of the paper "The Digital Cybersecurity Expert: How Far Have We Come?" presented in IEEE S&P 2025☆24May 21, 2025Updated 8 months ago
- Official implementation for "ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation"☆21Jan 31, 2026Updated 2 weeks ago
- LLM evaluation.☆16Nov 7, 2023Updated 2 years ago
- ☆28Mar 20, 2024Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆27Jun 11, 2025Updated 8 months ago