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。
☆64Apr 29, 2026Updated 6 months ago
Alternatives and similar repositories for Oyster
Users that are interested in Oyster are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The Strata-Sword is a hierarchical Chinese-English jailbreak safety benchmark based on quantified reasoning complexity, developed in-hous…☆21Sep 3, 2025Updated last year
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆80May 8, 2026Updated 5 months ago
- Shark Family is an AI safety red-teaming and jailbreak attack module. it harnesses powerful optimization and automated strategies to gene…☆15Oct 19, 2025Updated last year
- Self-Evolving Defense for AI Agents — Protect against prompt injection, data exfiltration, and multi-stage attacks with adaptive security…☆20Apr 8, 2026Updated 6 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆91Feb 26, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official PyTorch implementation of AAAI 2026 paper Geoshield☆14Apr 15, 2026Updated 6 months ago
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆15Apr 8, 2025Updated last year
- ☆11Oct 13, 2025Updated last year
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆20Aug 7, 2025Updated last year
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆75Nov 5, 2025Updated last year
- Official implementation of VIAT (Viewpoint-Invariant Adversarial Training) and GMVFool☆10Dec 26, 2023Updated 2 years ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆83Jun 11, 2026Updated 4 months ago
- Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency☆16Aug 6, 2025Updated last year
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Mar 29, 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.
- ☆24Dec 8, 2024Updated last year
- [CVPR 2025] Official implementation for JOOD "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"☆21Jun 11, 2025Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- ☆13Sep 29, 2025Updated last year
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆103Feb 3, 2026Updated 9 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆177Jun 27, 2025Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆91Jan 19, 2025Updated last year
- Repository for the Paper: Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Inj…☆21Apr 17, 2026Updated 6 months ago
- Two text jailbreak attacks against commercial black-box LLMs and a malicious content detection method, the latter of which is applied to …☆12Oct 21, 2026Updated 2 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Emoji Attack [ICML 2025]☆44Jul 15, 2025Updated last year
- Panda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).☆69Mar 23, 2026Updated 7 months ago
- Accepted by ECCV 2024☆222Oct 15, 2024Updated 2 years ago
- open Source code for propensity evaluation☆22Apr 25, 2026Updated 6 months ago
- ☆135Jul 29, 2026Updated 3 months ago
- [NDSS'25] The official implementation of safety misalignment.☆19Jan 8, 2025Updated last year
- Code for Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack(TPAMI 2025)☆43Aug 28, 2025Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆39Oct 23, 2024Updated 2 years ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆24Jul 2, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆62Jun 5, 2024Updated 2 years ago
- The code for ECCV2022 (Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal)☆45Oct 1, 2022Updated 4 years ago
- ☆66Aug 11, 2024Updated 2 years ago
- video_attack; Efficient Sparse Attacks on Videos using Reinforcement Learning☆15Oct 25, 2021Updated 5 years ago
- [ICCVW 2025 (Oral)] Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models☆28Sep 9, 2026Updated last month
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆15Jun 14, 2026Updated 4 months ago
- [NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models☆233Updated this week