12 citations · 18 across the 18 of their papers we have counts for
19 papers
Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
Chenlong Yin, Xiaolong Jin, Wei Zou +2
Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement lea…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
Weifei Jin, Xilong Wang, Wei Zou +2
Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into…
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
Yanting Wang, Chenlong Yin, Ying Chen +1
Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation,…
TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
Yanting Wang, Runpeng Geng, Jinghui Chen +2
Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful questio…
PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
Runpeng Geng, Yanting Wang, Chenlong Yin +3
Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existin…
UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
Runpeng Geng, Yanting Wang, Ying Chen +1
Retrieval-augmented generation (RAG) systems are widely deployed in real-world applications in diverse domains such as finance, healthcare, and cybersecurity. However, many studies…
RepoMark: A Data-Usage Auditing Framework for Code Large Language Models
Wenjie Qu, Yuguang Zhou, Bo Wang +4
The rapid development of Large Language Models (LLMs) for code generation has transformed software development by automating coding tasks with unprecedented efficiency. However, th…
TracLLM: A Generic Framework for Attributing Long Context LLMs
Yanting Wang, Wei Zou, Runpeng Geng +1
Long context large language models (LLMs) are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long co…
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
Zixuan Weng, Xiaolong Jin, Jinyuan Jia +1
Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass b…
Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
Jiate Li, Meng Pang, Yun Dong +2
Explaining Graph Neural Network (XGNN) has gained growing attention to facilitate the trust of using GNNs, which is the mainstream method to learn graph data. Despite their growing…
Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
Yuxin Yang, Qiang Li, Jinyuan Jia +2
Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vu…
Graph Neural Network Explanations are Fragile
Jiate Li, Meng Pang, Yun Dong +2
Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explan…
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
Yuan Xiao, Shiqing Ma, Juan Zhai +3
The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, withi…
TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
Yuzhou. Nie, Yanting. Wang, Jinyuan. Jia +4
One key challenge in backdoor attacks against large foundation models is the resource limits. Backdoor attacks usually require retraining the target model, which is impractical for…
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
Yanting Wang, Wei Zou, Jinyuan Jia
Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support sample…
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
Yanting Wang, Hongye Fu, Wei Zou +1
Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D poi…
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Wei Zou, Runpeng Geng, Binghui Wang +1
Large language models (LLMs) have achieved remarkable success due to their exceptional generative capabilities. Despite their success, they also have inherent limitations such as a…
Provably Robust Multi-bit Watermarking for AI-generated Text
Wenjie Qu, Wengrui Zheng, Tianyang Tao +6
Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive…