Phantivia / T-PGDLinks
[Findings of ACL 2023] Bridge the Gap Between CV and NLP! A Optimization-based Textual Adversarial Attack Framework.
☆14Updated 2 years ago
Alternatives and similar repositories for T-PGD
Users that are interested in T-PGD are comparing it to the libraries listed below
Sorting:
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆26Updated last year
- A curated list of trustworthy Generative AI papers. Daily updating...☆75Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆40Updated last year
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆45Updated last year
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆102Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆60Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆27Updated last year
- ☆53Updated 2 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆109Updated 2 years ago
- ☆36Updated last year
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 3 years ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆43Updated last year
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆63Updated 11 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆66Updated last year
- MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks…☆29Updated last year
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Updated 2 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆20Updated 2 years ago
- ☆32Updated last year
- ☆21Updated last year
- ☆24Updated 9 months ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆29Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆26Updated 4 years ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆54Updated 2 years ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆59Updated last year
- ☆33Updated 3 months ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆196Updated 2 years ago
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆57Updated 3 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆46Updated 3 years ago
- ☆114Updated 2 years ago