liuchengyuan123 / CPADLinks
The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".
☆20Updated last year
Alternatives and similar repositories for CPAD
Users that are interested in CPAD are comparing it to the libraries listed below
Sorting:
- ☆48Updated last year
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆267Updated 5 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆97Updated last year
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆108Updated 3 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆109Updated last year
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆34Updated last year
- This repo is for the paper: On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark☆24Updated 3 years ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆176Updated 2 years ago
- ☆27Updated 2 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆35Updated 4 years ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆105Updated 8 months ago
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆21Updated 2 years ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆170Updated 10 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆92Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆39Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆35Updated 2 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 3 years ago
- ☆90Updated last year
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆63Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆109Updated last year
- ☆28Updated last year
- Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge☆14Updated last year
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆96Updated 2 weeks ago
- A Domain-Specific Language, Jailbreak Attack Synthesizer and Dynamic LLM Redteaming Toolkit☆26Updated last year
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆33Updated 2 years ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆70Updated 2 years ago
- Multilingual safety benchmark for Large Language Models☆54Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆83Updated last year
- Recent papers on (1) Psychology of LLMs; (2) Biases in LLMs.☆50Updated 2 years ago