chichidd / llm-lora-trojanLinks
Code for paper "The Philosopherβs Stone: Trojaning Plugins of Large Language Models"
β18Updated 9 months ago
Alternatives and similar repositories for llm-lora-trojan
Users that are interested in llm-lora-trojan are comparing it to the libraries listed below
Sorting:
- π₯π₯π₯ Detecting hidden backdoors in Large Language Models with only black-box accessβ30Updated 3 weeks ago
- β24Updated 10 months ago
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Modelsβ37Updated 11 months ago
- β34Updated 8 months ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise aβ¦β97Updated 8 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agaiβ¦β47Updated 3 months ago
- Agent Security Bench (ASB)β89Updated last week
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wateβ¦β38Updated 7 months ago
- β28Updated 8 months ago
- β17Updated 4 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelsβ163Updated 4 months ago
- β58Updated 6 months ago
- β82Updated last year
- β29Updated 2 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safetyβ173Updated 4 months ago
- β26Updated 8 months ago
- β17Updated 3 weeks ago
- Repository for Towards Codable Watermarking for Large Language Modelsβ37Updated last year
- The official repository of the paper "The Digital Cybersecurity Expert: How Far Have We Come?" presented in IEEE S&P 2025β18Updated last month
- Code for paper "SrcMarker: Dual-Channel Source Code Watermarking via Scalable Code Transformations" (IEEE S&P 2024)β28Updated 10 months ago
- β16Updated 9 months ago
- β24Updated 3 years ago
- AI Model Security Reading Notesβ38Updated 3 months ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)β34Updated 2 months ago
- BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Modelsβ167Updated this week
- β21Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPTβ33Updated last year
- β24Updated 5 months ago
- Composite Backdoor Attacks Against Large Language Modelsβ16Updated last year
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"β15Updated 6 months ago