[ArXiv 2025] Imperceptible Jailbreaking against Large Language Models
☆25Oct 7, 2025Updated 10 months ago
Alternatives and similar repositories for imperceptible-jailbreaks
Users that are interested in imperceptible-jailbreaks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Apr 22, 2025Updated last year
- [ArXiv 2025] Denial-of-Service Poisoning Attacks on Large Language Models☆23Oct 22, 2024Updated last year
- [BMVC 2023] Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning☆17Sep 1, 2023Updated 2 years ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated last year
- The evaluation code for A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5☆53Jan 18, 2026Updated 6 months ago
- 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.
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆50Apr 8, 2024Updated 2 years ago
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆65Jan 5, 2026Updated 7 months ago
- ☆31Feb 19, 2025Updated last year
- Pytorch implementation of NPAttack☆12Jul 7, 2020Updated 6 years ago
- ☆15Oct 13, 2025Updated 9 months ago
- ☆108Feb 16, 2024Updated 2 years ago
- A Fine-grained Differentially Private Federated Learning against Leakage from Gradients☆16Jan 18, 2023Updated 3 years ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Oct 24, 2024Updated last year
- The code for the paper "Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval" (WWW'22, Oral).☆17Mar 8, 2022Updated 4 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- The implementatin of our ICLR 2021 work: Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits☆19Jul 20, 2021Updated 5 years ago
- [ICLR 2025] REFINE: Inversion-Free Backdoor Defense via Model Reprogramming☆13Feb 13, 2025Updated last year
- ☆16Jul 25, 2022Updated 4 years ago
- ☆32Mar 4, 2022Updated 4 years ago
- 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
- ☆23Jun 18, 2025Updated last year
- ☆15Feb 26, 2025Updated last year
- interesting & promising & widely adopted tricks for SOTA performance in machine learning community.☆15Apr 13, 2021Updated 5 years ago
- The official implementation for "Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space" (AC…☆15Nov 8, 2025Updated 9 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Code for "Variational Reasoning for Language Models"☆60Sep 29, 2025Updated 10 months ago
- DSN jailbreak Attack & Evaluation Ensemble☆17Feb 7, 2026Updated 6 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆231Dec 22, 2024Updated last year
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆18Dec 31, 2025Updated 7 months ago
- ☆20Mar 14, 2022Updated 4 years ago
- ☆18Jun 15, 2021Updated 5 years ago
- ☆12Mar 24, 2023Updated 3 years ago
- Adversarial detection and defense for deep learning systems using robust feature alignment☆17Nov 10, 2020Updated 5 years ago
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 8 months 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.
- ☆41May 29, 2026Updated 2 months ago
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆49Dec 4, 2024Updated last year
- [TMLR 2025] On Memorization in Diffusion Models☆33Oct 5, 2023Updated 2 years ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆66Jan 11, 2025Updated last year
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆70Sep 6, 2023Updated 2 years ago
- [ECCV-2024] Transferable Targeted Adversarial Attack, CLIP models, Generative adversarial network, Multi-target attacks☆39Apr 23, 2025Updated last year
- The code for the paper "Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders" (AAAI'24).☆39Dec 26, 2023Updated 2 years ago