Lucas-TY / llm_Implicit_referenceLinks
Official Implementation of implicit reference attack
☆11Updated last year
Alternatives and similar repositories for llm_Implicit_reference
Users that are interested in llm_Implicit_reference are comparing it to the libraries listed below
Sorting:
- Revisiting Character-level Adversarial Attacks for Language Models, ICML 2024☆19Updated 11 months ago
- ☆17Updated last year
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆51Updated 7 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆105Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆35Updated 2 years ago
- ☆23Updated last year
- ☆38Updated 8 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆60Updated 2 months ago
- ☆75Updated last year
- ☆14Updated last year
- A novel jailbreak attack unveiling an overlooked attack surface inherently in the chain-of-thought reasoning trajectory of LLMs☆22Updated 4 months ago
- ☆55Updated last year
- Code for Voice Jailbreak Attacks Against GPT-4o.☆36Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆92Updated last year
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆15Updated 5 months ago
- Code to conduct an embedding attack on LLMs☆30Updated last year
- Fine-tuning base models to build robust task-specific models☆34Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆30Updated 2 years ago
- ☆27Updated 4 years ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆68Updated last year
- ☆26Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆86Updated this week
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆190Updated 9 months ago
- The official repository for guided jailbreak benchmark☆28Updated 5 months ago
- [NDSS'25] The official implementation of safety misalignment.☆17Updated last year
- ☆37Updated last year
- ☆37Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆189Updated 6 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆45Updated last year