8 papers
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Jin Wei, Rundong Li, Ruihao Yang +10
Users commonly combine multiple Low-Rank Adaptation (LoRA) adapters to personalize images with different subjects, styles, and visual attributes. Yet inspecting adapters individual…
IDORacle: Template-Guided SQL-Sink Mediation for Object-Level Authorization in Java Applications
Yuewantong Song, Guanhang Shi, Yin Cai +5
Insecure Direct Object Reference (IDOR), often modeled as Broken Object-Level Authorization (BOLA), remains prevalent in Java database applications because identity and authorizati…
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content
Zhongli Fang, Yiran Chen, Lingyun Zhang +4
Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creating serious risks in critical…
Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks
Mingyu Luo, Ming Deng, Zilang Qiu +8
Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read…
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Haowen Xu, Xue Tan, Lei Ma +6
While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction l…
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption
Xue Tan, Yi Zheng, Chang Huo +7
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, effectively mitigating their inherent knowledge limitations. However…
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
Xue Tan, Hao Luan, Mingyu Luo +3
Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database, enabling them to produce responses that are more acc…
HuntFUZZ: Enhancing Error Handling Testing through Clustering Based Fuzzing
Jin Wei, Ping Chen, Jun Dai +4
Testing a program's capability to effectively handling errors is a significant challenge, given that program errors are relatively uncommon. To solve this, Software Fault Injection…