fzwark / Secure_LLM_SystemLinks
☆12Updated 7 months ago
Alternatives and similar repositories for Secure_LLM_System
Users that are interested in Secure_LLM_System are comparing it to the libraries listed below
Sorting:
- ☆36Updated last year
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆44Updated 4 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆17Updated last year
- ☆82Updated last month
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆34Updated 3 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆45Updated 2 months ago
- ☆35Updated 11 months ago
- ☆18Updated 3 years ago
- ☆23Updated last month
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆16Updated this week
- [NDSS'25] The official implementation of safety misalignment.☆16Updated 9 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆52Updated 6 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆91Updated last year
- ☆20Updated last year
- ☆16Updated last year
- ☆63Updated 9 months ago
- ☆27Updated last year
- [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models☆45Updated 8 months ago
- Code for Voice Jailbreak Attacks Against GPT-4o.☆34Updated last year
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"☆19Updated last month
- Agent Security Bench (ASB)☆124Updated this week
- Machine Learning & Security Seminar @Purdue University☆25Updated 2 years ago
- [EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models☆17Updated 7 months ago
- ☆25Updated 2 years ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17Updated last year
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning☆15Updated 8 months ago
- ☆35Updated last year
- ☆20Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆24Updated 10 months ago
- ☆21Updated 7 months ago