AI-secure / DecodingTrustLinks
A Comprehensive Assessment of Trustworthiness in GPT Models
☆310Updated last year
Alternatives and similar repositories for DecodingTrust
Users that are interested in DecodingTrust are comparing it to the libraries listed below
Sorting:
- 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…☆332Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆172Updated 11 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆156Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆171Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆175Updated 8 months ago
- ☆189Updated 2 years ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆116Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆248Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆303Updated 6 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆479Updated 8 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆152Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆404Updated 10 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆89Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆366Updated 10 months ago
- [ICML 2024] TrustLLM: Trustworthiness in Large Language Models☆615Updated 5 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆70Updated 9 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆107Updated 10 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆109Updated last year
- Python package for measuring memorization in LLMs.☆175Updated 4 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆97Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆79Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆75Updated 4 months ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆64Updated 2 years ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆155Updated last year
- ☆116Updated 5 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆107Updated last year
- ☆114Updated 2 years ago
- ☆39Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆201Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆60Updated 3 months ago