Trust4AI / ASTRAL
Automated Safety Testing of Large Language Models
☆14Updated 2 months ago
Alternatives and similar repositories for ASTRAL:
Users that are interested in ASTRAL are comparing it to the libraries listed below
- ☆59Updated 9 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆44Updated 3 weeks ago
- ☆67Updated last month
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆70Updated 2 months ago
- ☆59Updated 5 months ago
- ☆44Updated 11 months ago
- LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models☆19Updated 3 weeks ago
- Fine-tuning base models to build robust task-specific models☆29Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 8 months ago
- Agent Security Bench (ASB)☆76Updated 3 weeks ago
- ☆25Updated 2 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆45Updated 6 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆29Updated 4 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆116Updated 2 weeks ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆66Updated last year
- ☆33Updated 6 months ago
- CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.☆41Updated 5 months ago
- [ICLR 2025] Dissecting Adversarial Robustness of Multimodal LM Agents☆80Updated 2 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆50Updated 8 months ago
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆59Updated 5 months ago
- A prompt injection game to collect data for robust ML research☆55Updated 3 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆59Updated 3 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆73Updated last year
- ☆93Updated last month
- A re-implementation of the "Red Teaming Language Models with Language Models" paper by Perez et al., 2022☆28Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆100Updated last year
- ☆63Updated 3 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆148Updated 3 weeks ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆14Updated 8 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆135Updated 4 months ago