[ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
☆30Apr 19, 2026Updated 7 months ago
Alternatives and similar repositories for UltraBreak
Users that are interested in UltraBreak are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆32Nov 2, 2025Updated last year
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆47Feb 3, 2026Updated 9 months ago
- [CVPR 2026] Multi-Paradigm Collaborative Adversarial Attack Against Multimodal Large Language Models☆14Jul 15, 2026Updated 4 months ago
- ☆40Jun 13, 2026Updated 5 months ago
- [MM'25] JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering☆26Dec 23, 2025Updated 10 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.
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆37Dec 30, 2024Updated last year
- [EMNLP 2026 Findings] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs☆72Aug 26, 2026Updated 2 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆38Jun 1, 2025Updated last year
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 7 months ago
- Code Implementation of the Paper: One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Mod…☆14Jul 25, 2025Updated last year
- AdvT-shirt-1K A Physical-world Adversarial T-shirt Dataset for Adversarial Robustness Evaluation☆17Aug 7, 2025Updated last year
- Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness. (MD attacks)☆11Aug 29, 2020Updated 6 years ago
- [NeurIPS 2024] UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation☆10Jul 5, 2025Updated last year
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆76Aug 7, 2025Updated last year
- 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.
- The official website of the Open Trustworthy AI Community (OpenTAI).☆12Updated this week
- ☆85Jul 23, 2024Updated 2 years ago
- ☆56Dec 7, 2024Updated last year
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆18Jul 11, 2025Updated last year
- BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models☆17Oct 26, 2026Updated 3 weeks ago
- A guard model for Agent☆43Jul 15, 2026Updated 4 months ago
- [ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Promp…☆64May 8, 2026Updated 6 months ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆39Oct 29, 2025Updated last year
- ☆14Dec 29, 2025Updated 10 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.
- RLCDAlignBench: 44 alignment-failure detection benchmarks and code for 'Just Ask Jev' (RLCD zero-shot detector of AI alignment failures)☆31Sep 25, 2026Updated last month
- ☆73Updated this week
- Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation (AAAI 2026)☆15Aug 16, 2026Updated 3 months ago
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆16Jul 18, 2024Updated 2 years ago
- A simple implementation of BadNets on MNIST☆34Jul 29, 2019Updated 7 years ago
- Code to conduct an embedding attack on LLMs☆35Jan 10, 2025Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated 2 years ago
- [Machine Learning 2023] Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness☆18Jul 5, 2024Updated 2 years ago
- ☆26Oct 22, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official code repo for HazardAuditor☆23Sep 20, 2026Updated last month
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆75Nov 5, 2025Updated last year
- AutoPPT — AI-Powered Interactive Lecture Slides Generator | AI备课神器 | 一键生成一整周精美、可交互的课件!☆57Nov 2, 2026Updated 2 weeks ago
- [ICML2026] AudioMosaic: Contrastive Masked Audio Representation Learning☆29May 15, 2026Updated 6 months ago
- Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification☆14Dec 8, 2025Updated 11 months ago
- [ICML 2024] Sparse Model Inversion: Efficient Inversion of Vision Transformers with Less Hallucination☆15Apr 29, 2025Updated last year
- 让 Codex 在 CC Switch 的 OpenAI Official 与第三方 Provider 之间切换后,仍能继续原来的会话。Continue Codex sessions across OpenAI Official and third-party provid…☆16Oct 4, 2026Updated last month
Are these results useful?