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。
☆62Apr 29, 2026Updated 3 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:
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆75May 8, 2026Updated 3 months ago
- The Strata-Sword is a hierarchical Chinese-English jailbreak safety benchmark based on quantified reasoning complexity, developed in-hous…☆22Sep 3, 2025Updated 11 months ago
- Self-Evolving Defense for AI Agents — Protect against prompt injection, data exfiltration, and multi-stage attacks with adaptive security…☆19Apr 8, 2026Updated 4 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆89Feb 26, 2025Updated last year
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆15Apr 8, 2025Updated last year
- 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.
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Mar 29, 2024Updated 2 years ago
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆19Aug 7, 2025Updated 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
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆68Nov 5, 2025Updated 9 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆75Jun 11, 2026Updated 2 months ago
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆20Mar 31, 2025Updated last year
- 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 4 months ago
- [ICCVW 2025 (Oral)] Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models☆29Oct 20, 2025Updated 9 months ago
- 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.
- video_attack; Efficient Sparse Attacks on Videos using Reinforcement Learning☆15Oct 25, 2021Updated 4 years ago
- CVPR 2025 - R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning☆22Aug 28, 2025Updated 11 months ago
- [NDSS'25] The official implementation of safety misalignment.☆19Jan 8, 2025Updated last year
- The code for ECCV2022 (Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal)☆45Oct 1, 2022Updated 3 years ago
- [NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the…☆100Feb 3, 2026Updated 6 months ago
- Prompt Generator model for Stable Diffusion Models☆12Jun 20, 2023Updated 3 years ago
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆15Jul 18, 2024Updated 2 years ago
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆39Apr 23, 2025Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆177Jun 27, 2025Updated last year
- 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.
- Accepted by ECCV 2024☆218Oct 15, 2024Updated last year
- Improving fast adversarial training with prior-guided knowledge (TPAMI2024)☆43Apr 21, 2024Updated 2 years ago
- ☆24Dec 8, 2024Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- ☆134Jul 29, 2026Updated 2 weeks ago
- ☆61Jun 5, 2024Updated 2 years ago
- 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
- Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency☆16Aug 6, 2025Updated last year
- ☆24Feb 17, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆52Jan 15, 2026Updated 7 months ago
- ☆20Jun 4, 2026Updated 2 months 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 last year
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆61Jun 15, 2022Updated 4 years ago
- ☆19Oct 20, 2024Updated last year
- Global AI Safety and Governance: Never Compromise to Vulnerabilities☆44Sep 11, 2025Updated 11 months ago
- Code for Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack(TPAMI 2025)☆42Aug 28, 2025Updated 11 months ago