Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime
☆59Sep 19, 2023Updated 3 years ago
Alternatives and similar repositories for image-hijacks
Users that are interested in image-hijacks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆288May 13, 2024Updated 2 years ago
- ☆102Oct 15, 2023Updated 3 years ago
- ☆62Jun 5, 2024Updated 2 years ago
- The implementation of our IEEE S&P 2024 paper "Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples".☆11Jun 28, 2024Updated 2 years ago
- [ACM MM 2022] Official PyTorch implementation of Towards Adversarial Attack on Vision-Language Pre-training Models (Co-Attack)☆69Mar 20, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆56Dec 7, 2024Updated last year
- [NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models☆233Updated this week
- ☆109Feb 16, 2024Updated 2 years ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆217Jun 26, 2025Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆36Dec 30, 2024Updated last year
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆91Nov 28, 2023Updated 2 years ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆95Jun 6, 2024Updated 2 years ago
- ☆66Aug 11, 2024Updated 2 years ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 4 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.
- [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
- Universal Adversarial Perturbations for Vision-Language Pre-trained Models☆25Aug 8, 2025Updated last year
- ☆14Jan 14, 2026Updated 9 months ago
- Code to conduct an embedding attack on LLMs☆35Jan 10, 2025Updated last year
- ☆11Apr 28, 2024Updated 2 years ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆60Apr 25, 2026Updated 6 months ago
- Code and data for "ImgTrojan: Jailbreaking Vision-Language Models with ONE Image"☆24Mar 26, 2025Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated 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.
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models☆336Jan 11, 2026Updated 9 months ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆165Feb 19, 2026Updated 8 months ago
- ☆15Oct 6, 2024Updated 2 years ago
- ☆82Jan 21, 2026Updated 9 months ago
- Agent Data Injection (ADI) Attacks☆15Jul 13, 2026Updated 3 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated 2 years ago
- [ICLR 2026] Data and Code for Paper Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models☆14Feb 2, 2026Updated 9 months ago
- ☆51Jul 14, 2024Updated 2 years ago
- Accepted by ECCV 2024☆222Oct 15, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆75Oct 23, 2024Updated 2 years ago
- Official codes for GRA (Accepted by ICCV2023)☆17Jul 18, 2023Updated 3 years ago
- ☆13Feb 11, 2026Updated 8 months ago
- A list of papers in NeurIPS 2022 related to adversarial attack and defense / AI security.☆78Dec 5, 2022Updated 3 years ago
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆117Jul 21, 2022Updated 4 years ago
- [NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"☆15Oct 22, 2025Updated last year
- Official Pytorch implementation for "Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization" (CVPR 20…☆27Jul 18, 2023Updated 3 years ago