idllresearch / malicious-gpt
[USENIX Security '24] Dataset associated with real-world malicious LLM applications, including 45 malicious prompts for generating malicious content, malicious responses from LLMs, 182 real-world jailbreak prompts, keywords related to LLMs, etc.
☆60Updated 6 months ago
Alternatives and similar repositories for malicious-gpt:
Users that are interested in malicious-gpt are comparing it to the libraries listed below
- ☆29Updated last month
- Practical Detection of Trojan Neural Networks☆119Updated 4 years ago
- [ICLR Workshop 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆105Updated last month
- PhishIntention: Phishing detection through webpage intention☆249Updated 3 weeks ago
- [CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models☆129Updated 3 weeks ago
- Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging (TIFS2024)☆34Updated 10 months ago
- [NDSS'24] Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time☆55Updated 6 months ago
- Using Wasserstein Generative Adversarial Network to fool intrusion detection systems (IDS) into believing that malicious traffic is norma…☆72Updated last year
- Improving fast adversarial training with prior-guided knowledge (TPAMI2024)☆41Updated last year
- Code for ACL 2024 long paper: Are AI-Generated Text Detectors Robust to Adversarial Perturbations?☆28Updated 9 months ago
- ☆117Updated 3 weeks ago
- Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)☆95Updated 2 weeks ago
- ☆73Updated 2 months ago
- Code for Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack☆33Updated 5 months ago
- [ACL 2024] CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and …☆97Updated 8 months ago
- A benchmark for logging statement generation.☆21Updated 5 months ago
- Secure Transformer Inference is a protocol for serving Transformer-based models securely.☆92Updated 11 months ago
- ☆16Updated 6 months ago
- ☆78Updated 4 months ago
- Crack Vigenere Ciphertext using statistic method (Index of Coincidence and Chi-square)☆18Updated last year
- [NeurIPS 2024] EffiBench: Benchmarking the Efficiency of Automatically Generated Code☆51Updated 4 months ago
- [NeurIPS 2024] GuardT2I: Defending Text-to-Image Models from Adversarial Prompts☆38Updated 5 months ago
- Source code for "CoEdPilot: Recommending Code Edits with Learned Prior Edit Relevance, Project-wise Awareness, and Interactive Nature"☆99Updated 3 weeks ago
- This project help you understand the concepts of histogram equalization and histogram specification in image processing learning from a p…☆9Updated last year
- Tensorflow环境下，基于CNN算法，KD99与网络数据训练集共3000w数据训练，在19w数据与1w攻检验下，模型准确率为92.8%.☆62Updated 3 years ago
- alsap_frontend☆23Updated 2 months ago
- use sklearn to detect two types of network attacks☆32Updated 5 years ago
- ☆34Updated 3 months ago
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆24Updated last year
- [ICML22] "Revisiting and Advancing Fast Adversarial Training through the Lens of Bi-level Optimization" by Yihua Zhang*, Guanhua Zhang*, …☆65Updated 2 years ago