kztakemoto / simbaja
All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
☆16Updated last year
Alternatives and similar repositories for simbaja:
Users that are interested in simbaja are comparing it to the libraries listed below
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆38Updated 5 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆19Updated 8 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆23Updated last year
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆12Updated 5 months ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆28Updated 4 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆61Updated 5 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆51Updated 8 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆21Updated 9 months ago
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆37Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆51Updated last month
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆23Updated 8 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆60Updated 3 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆52Updated 11 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆14Updated last month
- ☆20Updated last year
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?☆21Updated 2 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 6 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆55Updated this week
- ☆81Updated 2 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆32Updated this week
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆70Updated 6 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆45Updated 6 months ago
- ☆20Updated 4 months ago
- ☆25Updated 6 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆20Updated 5 months ago
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆16Updated 9 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 5 months ago
- Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"☆56Updated 5 months ago
- ☆40Updated 10 months ago
- 🔥🔥🔥Breaking long thought processes of o1-like LLMs, such as DeepSeek-R1, QwQ☆28Updated last month