[ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
☆28Apr 19, 2026Updated 3 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☆31Nov 2, 2025Updated 9 months ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆48Feb 3, 2026Updated 6 months ago
- ☆30Jun 13, 2026Updated last month
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year
- Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness. (MD attacks)☆11Aug 29, 2020Updated 5 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 4 months ago
- [MM'25] JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering☆22Dec 23, 2025Updated 7 months ago
- Code to conduct an embedding attack on LLMs☆34Jan 10, 2025Updated last year
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆18Jul 11, 2025Updated last year
- The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)☆15Jul 18, 2024Updated 2 years ago
- [ICML 2026] JustAsk: Curious Code Agents Reveal System Prompts in Frontier LLMs | Verified on Claude Code | Autoresearch for System Promp…☆57May 8, 2026Updated 3 months ago
- ☆21Jun 12, 2026Updated last month
- [IEEE TDSC] Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks☆16Oct 7, 2025Updated 10 months ago
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated 10 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining☆23Feb 26, 2025Updated last year
- ☆46Mar 18, 2026Updated 4 months ago
- A simple implementation of BadNets on MNIST☆34Jul 29, 2019Updated 7 years ago
- Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic Sys…☆124Updated this week
- Code for Paper: Benchmarking Multi-step Scientific Tool-use in LLM Agents☆38Jul 5, 2026Updated last month
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆74Aug 7, 2025Updated last year
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆44Mar 16, 2026Updated 4 months ago
- Code for Transferable Unlearnable Examples☆22Mar 11, 2023Updated 3 years ago
- ☆15Jun 2, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety☆276Apr 12, 2026Updated 3 months ago
- Strongest attack against Feature Scatter and Adversarial Interpolation☆25Dec 26, 2019Updated 6 years ago
- [ICLR2023] Distilling Cognitive Backdoor Patterns within an Image☆37Oct 29, 2025Updated 9 months ago
- [NeurIPS 2023] Content-based Unrestricted Adversarial Attack☆31Jul 21, 2025Updated last year
- ☆26Mar 24, 2023Updated 3 years ago
- [NDSS 2026] Official repo for Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography☆59Mar 14, 2026Updated 4 months ago
- [ICLR'26] Official code for "Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Trai…☆16Mar 31, 2026Updated 4 months ago
- ISC☆934Updated this week
- ☆10Dec 25, 2023Updated 2 years 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.
- ☆17Nov 24, 2025Updated 8 months ago
- What do we learn from inverting CLIP models?☆58Mar 6, 2024Updated 2 years ago
- Composite Backdoor Attacks Against Large Language Models☆25Apr 12, 2024Updated 2 years ago
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆44Apr 28, 2026Updated 3 months ago
- Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering [ACM MM'24]☆10Jul 22, 2024Updated 2 years ago
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment (NeurIPS 2025)☆67Nov 5, 2025Updated 9 months ago
- [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models☆322Mar 13, 2026Updated 4 months ago