This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.
☆61Dec 20, 2024Updated last year
Alternatives and similar repositories for USC
Users that are interested in USC are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Simulator.☆101Apr 21, 2025Updated last year
- [ACL 2024] The official GitHub repo for the paper "The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Pe…☆82Jul 19, 2024Updated last year
- Official code for the ICCV2023 paper ``One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training''☆20Aug 9, 2023Updated 2 years ago
- Official Code for ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users (NeurIPS 2024)☆24Oct 23, 2024Updated last year
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Jun 7, 2023Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆20Oct 2, 2024Updated last year
- ☆11Dec 18, 2024Updated last year
- [KDD 2024] Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination☆29May 27, 2025Updated 11 months ago
- A Easily Extensible labeling annotation template web tool (Flask + Vue 3) for annotation [易扩展的标注网页模板]☆26Apr 22, 2025Updated last year
- ☆68Sep 29, 2020Updated 5 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆27Apr 29, 2020Updated 6 years ago
- SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification☆15Jun 10, 2025Updated 10 months ago
- Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)☆144Apr 7, 2025Updated last year
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆16Oct 24, 2024Updated 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.
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆58May 1, 2026Updated last week
- An evaluation framework for mitigating DNN backdoor attacks using data augmentations☆11Dec 10, 2020Updated 5 years ago
- ☆60Jun 13, 2024Updated last year
- Take further steps in the arms race of adversarial examples with only preprocessing.☆36Aug 4, 2020Updated 5 years ago
- https://footprints.baulab.info☆18Oct 4, 2024Updated last year
- ☆10Oct 31, 2022Updated 3 years ago
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Mar 29, 2024Updated 2 years ago
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆15Apr 20, 2024Updated 2 years ago
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆35Jan 31, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆23Apr 23, 2024Updated 2 years ago
- Code and data release of the paper Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows☆15Oct 4, 2024Updated last year
- ☆27Jun 5, 2024Updated last year
- Injecting watermarks to protein sequences for privacy protection in biosecurity☆10Oct 1, 2024Updated last year
- ☆12May 6, 2022Updated 4 years ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆47Feb 28, 2023Updated 3 years ago
- [ICLR 2025] REFINE: Inversion-Free Backdoor Defense via Model Reprogramming☆13Feb 13, 2025Updated last year
- ☆57Jul 27, 2022Updated 3 years ago
- Implemention of "Piracy Resistant Watermarks for Deep Neural Networks" in TensorFlow.☆12Dec 5, 2020Updated 5 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official Implementation for "Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approxim…☆12Aug 14, 2024Updated last year
- The official code for ``An Engorgio Prompt Makes Large Language Model Babble on''☆22Aug 9, 2025Updated 9 months ago
- This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calc…☆12Feb 14, 2023Updated 3 years ago
- This is the code for semi-supervised robust training (SRT).☆18Mar 24, 2023Updated 3 years ago
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆68Mar 2, 2026Updated 2 months ago
- Code for identifying natural backdoors in existing image datasets.☆15Aug 24, 2022Updated 3 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆53Nov 16, 2022Updated 3 years ago