LostOxygen / llm-confidentiality
Whispers in the Machine: Confidentiality in LLM-integrated Systems
☆35Updated last month
Alternatives and similar repositories for llm-confidentiality:
Users that are interested in llm-confidentiality are comparing it to the libraries listed below
- [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
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆44Updated 2 weeks ago
- LLM security and privacy☆48Updated 6 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆62Updated last year
- Risks and targets for assessing LLMs & LLM vulnerabilities☆30Updated 10 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆73Updated last year
- ☆23Updated 8 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆148Updated 3 weeks ago
- Code to break Llama Guard☆31Updated last year
- Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the Over…☆12Updated last year
- This repository provides a benchmark for prompt Injection attacks and defenses☆188Updated last week
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆70Updated 2 months ago
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆111Updated 10 months ago
- ☆54Updated 4 months ago
- ☆44Updated 2 years ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆45Updated 6 months ago
- ☆59Updated 9 months ago
- ☆67Updated last month
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆62Updated 5 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆114Updated 2 weeks ago
- [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`☆67Updated last month
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆66Updated last year
- ☆86Updated last year
- ☆59Updated 5 months ago
- ☆170Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆130Updated 3 weeks ago
- Agent Security Bench (ASB)☆76Updated 3 weeks ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆52Updated 8 months ago