shadowkiller33 / Language_attackLinks
A repo for LLM jailbreak
☆14Updated last year
Alternatives and similar repositories for Language_attack
Users that are interested in Language_attack are comparing it to the libraries listed below
Sorting:
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆81Updated last year
- ☆17Updated 5 months ago
- ☆18Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆103Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆85Updated 4 months ago
- ☆181Updated last year
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆21Updated 5 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆95Updated 3 months ago
- ☆11Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆110Updated 6 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆58Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆34Updated last year
- ☆83Updated 8 months ago
- ☆31Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆318Updated last year
- Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge☆14Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆55Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆128Updated this week
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Updated 10 months ago
- Multilingual safety benchmark for Large Language Models☆52Updated last year
- A new algorithm that formulates jailbreaking as a reasoning problem.☆23Updated 2 months ago
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆99Updated 3 weeks ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆54Updated 2 years ago
- [ICLR 2025] General-purpose activation steering library☆99Updated this week
- ☆25Updated 2 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆53Updated last year
- Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper☆79Updated 4 years ago
- ☆41Updated 11 months ago