Search Results for author:
Found 5 papers, 1 papers with code
Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
Our benchmark covers 5 standard question answering (QA) datasets and 10 expanded variants, along with 13 poisoning attack methods and 7 defense mechanisms, representing a broad spectrum of existing techniques.
When Safety Detectors Aren't Enough: A Stealthy and Effective Jailbreak Attack on LLMs via Steganographic Techniques
Jailbreak attacks pose a serious threat to large language models (LLMs) by bypassing built-in safety mechanisms and leading to harmful outputs.
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks.
Practical Poisoning Attacks against Retrieval-Augmented Generation
Large language models (LLMs) have demonstrated impressive natural language processing abilities but face challenges such as hallucination and outdated knowledge.
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, particularly, the API misuse and model extraction attacks.
