6 papers
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Hanxi Li, Jianan Zhou, Jiale Lao +5
Vector databases serve as the retrieval backbone of modern AI applications, yet their security remains largely unexplored. We propose the Black-Hole Attack, a poisoning attack that…
QUITE: A Query Rewrite System Beyond Rules with LLM Agents
Yuyang Song, Hanxu Yan, Jiale Lao +5
Query rewrite transforms SQL queries into semantically equivalent forms that run more efficiently. Existing approaches mainly rely on predefined rewrite rules, but they handle a li…
Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks
Meiyu Lin, Haichuan Zhang, Jiale Lao +5
Large language models (LLMs) have shown state-of-the-art results in translating natural language questions into SQL queries (Text-to-SQL), a long-standing challenge within the data…
CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning
Renyuan Li, Zhibo Liang, Haichuan Zhang +5
Recent breakthroughs in text-to-speech (TTS) voice cloning have raised serious privacy concerns, allowing highly accurate vocal identity replication from just a few seconds of refe…
GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization
Jiale Lao, Yibo Wang, Yufei Li +6
Modern database management systems (DBMS) expose hundreds of configurable knobs to control system behaviours. Determining the appropriate values for these knobs to improve DBMS per…
Attack as Defense: Run-time Backdoor Implantation for Image Content Protection
Haichuan Zhang, Meiyu Lin, Zhaoyi Liu +4
As generative models achieve great success, tampering and modifying the sensitive image contents (i.e., human faces, artist signatures, commercial logos, etc.) have induced a signi…