Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
☆24Dec 9, 2021Updated 4 years ago
Alternatives and similar repositories for SOS
Users that are interested in SOS are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆45Sep 11, 2022Updated 3 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆48Oct 12, 2022Updated 3 years ago
- [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks☆13Feb 26, 2023Updated 3 years ago
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆16Jun 29, 2021Updated 5 years ago
- TrojanLM: Trojaning Language Models for Fun and Profit☆16Jun 17, 2021Updated 5 years 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.
- Hidden backdoor attack on NLP systems☆45Nov 14, 2021Updated 4 years ago
- ☆18Aug 15, 2022Updated 3 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆41Jul 8, 2024Updated 2 years ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆16Oct 14, 2024Updated last year
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆44Jul 26, 2021Updated 5 years ago
- The code implementation of MuScleLoRA (Accepted in ACL 2024)☆10Dec 1, 2024Updated last year
- The code implementation of GraCeFul (Accepted in COLING 2025)☆13Jan 27, 2025Updated last year
- ☆18Jul 1, 2021Updated 5 years ago
- ☆19Mar 9, 2024Updated 2 years 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.
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆15Jun 21, 2024Updated 2 years ago
- ☆28Nov 9, 2022Updated 3 years ago
- This repository contains code implementation of the paper "AI-Guardian: Defeating Adversarial Attacks using Backdoors, at IEEE Security a…☆14Aug 13, 2023Updated 3 years ago
- ☆29Aug 21, 2023Updated 2 years ago
- [ICSE-SEIP'21] Robustness of on-device Models: AdversarialAttack to Deep Learning Models on Android Apps☆15Jun 2, 2022Updated 4 years ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆211Apr 10, 2023Updated 3 years ago
- [ACL 2025] Cautious Next Token Prediction☆16Jul 24, 2025Updated last year
- ☆71Feb 4, 2024Updated 2 years ago
- Implementation of "Adversarial Text Generation without Reinforcement Learning"☆12Mar 13, 2019Updated 7 years 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.
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆117Sep 27, 2024Updated last year
- Natural Universal Trigger Search (NUTS)☆21Apr 17, 2021Updated 5 years ago
- verifying machine unlearning by backdooring☆20Mar 25, 2023Updated 3 years ago
- Official Repository for the CVPR 2020 paper "Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs"☆45Oct 24, 2023Updated 2 years ago
- ☆13Oct 21, 2021Updated 4 years ago
- This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan …☆10Mar 7, 2021Updated 5 years ago
- ☆17Jun 27, 2021Updated 5 years ago
- ☆25Oct 11, 2024Updated last year
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆32Jul 11, 2022Updated 4 years 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.
- ☆25Aug 21, 2024Updated last year
- ☆19Feb 10, 2022Updated 4 years ago
- This is a python script to generate nice bibtex file for latex.☆19Mar 1, 2020Updated 6 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Nov 18, 2024Updated last year
- The code and data for ACL2021 paper <Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?>☆22Dec 18, 2022Updated 3 years ago
- Fingerprint large language models☆52Jul 11, 2024Updated 2 years ago
- Official Implementation for "Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approxim…☆12Aug 14, 2024Updated last year