Composite Backdoor Attacks Against Large Language Models
☆25Apr 12, 2024Updated last year
Alternatives and similar repositories for CBA
Users that are interested in CBA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆22Sep 16, 2022Updated 3 years ago
- ☆26Aug 21, 2024Updated last year
- ICL backdoor attack☆17Nov 4, 2024Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆21Aug 10, 2024Updated last year
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆55Jun 2, 2025Updated 10 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆22Jul 3, 2024Updated last year
- Machine Learning & Security Seminar @Purdue University☆25May 9, 2023Updated 2 years ago
- ☆19Nov 6, 2023Updated 2 years ago
- ☆23Aug 24, 2020Updated 5 years ago
- A toolbox for backdoor attacks.☆23Jan 13, 2023Updated 3 years ago
- This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".☆15Sep 5, 2023Updated 2 years ago
- Code used to run experiments for the ICLR 2023 paper "Computational Language Acquisition with Theory of Mind".☆15Apr 27, 2023Updated 2 years ago
- An online AI security course created by UChicago's XLab☆31Feb 21, 2026Updated last month
- Code implementation for paper AbsenceBench: Language Models Can't Tell What's Missing☆18Oct 23, 2025Updated 5 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- AlgZoo: uninterpreted models with fewer than 1,500 parameters☆47Jan 19, 2026Updated 2 months ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆29Dec 31, 2024Updated last year
- ☆29Aug 21, 2023Updated 2 years ago
- This repository contains the source code for "Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble", In Pro…☆10Jan 2, 2026Updated 3 months ago
- ☆42Dec 17, 2025Updated 3 months ago
- [SIGIR'25] Code of "Generative Recommender with End-to-End Learnable Item Tokenization".☆26Apr 17, 2025Updated 11 months ago
- ☆27Nov 9, 2022Updated 3 years ago
- ☆26Dec 1, 2022Updated 3 years ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆28Dec 2, 2025Updated 4 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- 专用于搭建MT4或MT5交易跟单平台☆27Apr 2, 2026Updated last week
- Official Implementation for "Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approxim…☆12Aug 14, 2024Updated last year
- ☆37Oct 17, 2024Updated last year
- Gaussian Membership Inference Privacy (NeurIPS 2023)☆12Jul 27, 2024Updated last year
- Official GitHub repository for the paper "Adversarial Attacks on Robotic Vision Language Action Models"☆31May 28, 2025Updated 10 months ago
- Capstone Project: Reversing Image Redaction with Deep Learning☆12Nov 18, 2016Updated 9 years ago
- ☆13Jun 1, 2024Updated last year
- [IEEE TIP] Offical implementation for the work "BadCM: Invisible Backdoor Attack against Cross-Modal Learning".☆14Aug 30, 2024Updated last year
- 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.
- Watermarking LLM papers up-to-date☆11Dec 17, 2023Updated 2 years ago
- bert蒸馏实践，包含BiLSTM蒸馏BERT和TinyBert☆13Apr 23, 2022Updated 3 years ago
- some baseline attack method by pytorch☆11Oct 13, 2021Updated 4 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Sep 11, 2022Updated 3 years ago
- ☆16Mar 31, 2025Updated last year
- SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations☆14Jan 6, 2022Updated 4 years ago
- Distilling Task-Specific Knowledge from BERT into Simple Neural Networks.☆15Aug 28, 2020Updated 5 years ago