RylanSchaeffer / AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer
Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
☆20Updated last week
Alternatives and similar repositories for AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer:
Users that are interested in AstraFellowship-When-Do-VLM-Image-Jailbreaks-Transfer are comparing it to the libraries listed below
- ☆31Updated 8 months ago
- ☆30Updated 3 months ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆23Updated 2 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆16Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆17Updated 4 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 7 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆50Updated 6 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆40Updated 8 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆22Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆57Updated last month
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆36Updated 4 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆55Updated 4 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆47Updated 7 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆42Updated last month
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆60Updated 5 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆75Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆74Updated 7 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆50Updated 10 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆16Updated 10 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 10 months ago
- [ICLR 2025] Dissecting Adversarial Robustness of Multimodal LM Agents☆68Updated last week
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆9Updated 7 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆56Updated last month
- ☆41Updated 2 months ago
- ☆15Updated this week
- ☆11Updated last year
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆44Updated last year
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆39Updated 3 months ago
- ☆47Updated 7 months ago